Compare commits

...
Author SHA1 Message Date
James PineandClaude Opus 4.7 4ffbc03d15 fix(audio): raise trim threshold, cap pad at net-neutral
Review feedback on the preprocessor:

1. ``trim_top_db=30`` was labelled "conservative" in the docstring but is
   actually *more* aggressive than librosa's default of 60. Normal
   speech dynamic range sits around 30 dB, so 30 dB would eat quiet
   trailing syllables and soft consonants. Raise the default to 40 dB —
   below normal speech dynamic range but still catching obvious edge
   silence — and fix the docstring.

2. Unconditional 100 ms edge padding ran even when ``librosa.effects.trim``
   removed nothing. For a well-recorded 29.9 s upload that path would
   push the waveform past the 30 s ceiling and trigger a spurious "too
   long" rejection. Only pad when trimming actually shortened the
   audio, and cap the pad so the output never exceeds the input length.

Adds a regression test for the net-neutral length behaviour.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-19 18:25:52 -07:00
James PineandClaude Opus 4.7 a49cc6afbb fix(audio): preprocess reference samples instead of rejecting them
Uploaded/recorded voice samples were rejected outright whenever the peak
exceeded 0.99 ("Audio is clipping (reduce input gain)"). That wasn't
actionable: a recording in the app has no pre-gain control, and an
already-captured file can't be re-taken by the user. The Settings
"Normalize audio" toggle only affects generated TTS output, so users who
enabled it expecting it to help with sample uploads were still blocked.

Replace the hard reject with a small, always-on preprocess step that
runs right after load:
  - DC-offset removal
  - Conservative edge-silence trim (top_db=30) with 100 ms padding kept
  - Peak cap at 0.95 if the input peak exceeds that

Duration and RMS checks now run on the preprocessed waveform, so
samples that were previously rejected for being "hot" are accepted and
stored with safe headroom. True in-waveform clipping artifacts still
can't be repaired — peak scaling only prevents downstream re-clipping
during multi-sample combination and TTS inference.

Adds a unit-test file (previously none existed for audio.py).

Fixes #456.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-19 16:41:10 -07:00
Shekhar KumarandGitHub e3f7cd9d00 fix(landing): use public origin for download redirects behind proxies (#498)
Prefer x-forwarded host/proto for redirect URL construction so users are not sent to internal localhost origins.

Fixes #496
2026-04-19 15:57:58 -07:00
27a5a62581 fix(landing): API example + new /download page (no more dumping users on GitHub) (#487)
* fix(landing): use qwen_custom_voice in API example (instruct is CustomVoice-only)

The curl snippet showed engine: "qwen" alongside an instruct field, but base
Qwen3-TTS has no instruct path — that's a Qwen CustomVoice feature.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(landing): use a realistic UUID for profile_id in API example

Profile IDs are str(uuid.uuid4()), not slugs (see backend/services/profiles.py:175).

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* feat(landing): add polished /download page — no more dumping users on GitHub

Users were clicking download, landing on the GitHub releases page, and filing
confused comments along the lines of "I ended up on some blog site called
GitHub." We now route every download CTA through a dedicated /download page
that auto-triggers the platform-specific download and gives users a polished
post-click experience with donate + docs + AI help prompts.

- New /download page:
  - Big app logo + "Your download has started" messaging.
  - Auto-detects platform from ?platform=X or navigator.userAgent.
  - Programmatically clicks a hidden anchor to trigger the file download
    without leaving the page.
  - Platform-specific buttons as a visible fallback for "download not
    working" / manual-pick.
  - Personal donate spiel + Buy Me a Coffee button.
  - Resources grid: docs, DeepWiki ("got questions? ask AI"), GitHub.
- Landing page download section cards now link to /download?platform=X
  instead of the asset URL directly.
- /download/[platform] (used by README/docs links) now redirects to the
  /download page rather than straight to the asset or to GitHub on error.
- Drops unused downloadLinks state from the landing page.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(landing): use official platform brand icons via simple-icons

The hand-rolled Linux SVG path wasn't actually Tux — it was a symmetric
placeholder shape. Apple/Windows were close but not canonical either.

- Apple + Linux: pulled from @icons-pack/react-simple-icons (SiApple, SiLinux).
- Windows: simple-icons drops the Microsoft mark over trademark policy, so
  the Windows 11 flag is inlined from Microsoft's public brand guidance.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(landing): route Download CTAs to /download page, not the section anchor

Hero CTA, navbar link, and footer link were all scrolling to #download
(the section at the bottom of the page) instead of going to the new
/download page that triggers the actual download.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* chore(landing): run dev server on Node instead of Bun runtime

Bun runtime + Next 16 Turbopack dev server intermittently trips a
JavaScriptCore allocator panic ('pas panic: deallocation did fail ...
Alloc bit not set') after a few requests. Dropping --bun keeps Bun as
the package manager but runs next dev on Node, which is stable.

Build + start keep --bun since one-shot invocations don't exhibit the
allocator drift.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(landing): route Linux users to /linux-install instead of attempting download

No prebuilt Linux binary exists yet (see /linux-install for build-from-source
instructions). The /download page previously treated Linux like the other
platforms — auto-triggering a non-existent AppImage and offering a dead
manual button.

- /download page: if platform resolves to 'linux' via ?platform or UA detect,
  window.location.replace('/linux-install') — never try to auto-download.
- Manual Linux card: label changed to "Build from source" and links to
  /linux-install (no download attribute, no asset URL).
- /download/linux pretty URL: 307s straight to /linux-install.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* docs: consolidate troubleshooting into the MDX docs site + status updates

- Delete docs/TROUBLESHOOTING.md; the canonical troubleshooting guide now
  lives under docs/content/docs/overview/troubleshooting.mdx so it's served
  from docs.voicebox.sh alongside the rest of the docs.
- CONTRIBUTING.md + README.md: repoint "Troubleshooting" references to the
  new MDX path. README gets a top-level callout so users hit the guide
  before filing an issue.
- PROJECT_STATUS.md: refresh issue/PR counts, document the flash-attn
  warning (cosmetic on all platforms; CUDA-only, fallback is PyTorch SDPA
  which is near-FA2 on Ampere+) with per-platform context + community
  Windows wheels + SageAttention/xformers alternatives, add WebAudio
  audio-session bug note (tracked separately in PR #486), and expand the
  Qwen 0.6B→1.7B MLX fallback explanation for triage.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(landing): address PR #487 review feedback

- Preserve canonical camelCase platform aliases (macArm, macIntel) in the
  /download/[platform] redirect so those URLs don't lose their platform param.
- Add accessible title + role="img" to the inline Windows SVG so it passes
  Biome's a11y rule and announces to screen readers.
- On /api/releases fetch failure, show an explicit error state with a single
  intentional link to GitHub releases — no more silent GitHub fallback or
  disabled-button UX lie. Keeps normies off GitHub unless they opt in.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 23:32:32 -07:00
d3a44338a2 fix(audio): prevent WKWebView audio session teardown after backgrounding (#41) (#486)
Keep a silent looping <audio> element mounted at the app root so macOS
never tears down the CoreAudio session. Without this, backgrounding the
app long enough leaves WaveSurfer's AudioContext in a state where play()
resolves and timeupdate fires, but no audio reaches the output — and not
even cmd+R (full JS reload) restores it, only a full app relaunch.

Uses a zero-PCM WAV blob at full volume rather than a muted element,
since WebKit can optimize muted media away and defeat the purpose.

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 22:43:59 -07:00
James Pine 28aa963b09 readme update 2026-04-18 21:19:51 -07:00
ae91aa9a88 docs: audit mdx docs against multi-engine backend (#484)
* docs: audit mdx docs against multi-engine backend and refresh stale content

Rewrote developer-facing docs that predated the TTSBackend Protocol /
ModelConfig registry refactor (architecture, tts-generation,
model-management, transcription). Updated user-facing docs to reflect all
seven shipped engines (Qwen, Qwen CustomVoice, LuxTTS, Chatterbox,
Chatterbox Turbo, TADA, Kokoro) instead of the outdated "5 engines" claim.

Also fixes:
- Stale app identifier (com.voicebox.app → sh.voicebox.app)
- CUDA backend update flow (now two-archive split, not N-way chunks)
- Whisper model list (removed tiny, added turbo)
- Broken /development/ and /guides/ route links
- Stale just commands and install steps (missing --no-deps chatterbox/tada)
- Removed ASCII art diagrams from README and stories.mdx
- History Generation schema sync with DB model

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* docs: add DeepWiki badge to README

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* docs: address PR review feedback

- architecture.mdx: fix backends/ file list (remove nonexistent qwen_backend.py, rename tada_backend.py → hume_backend.py)
- model-management.mdx: Kokoro language count 9 → 8 (matches ModelConfig)
- model-management.mdx: ProgressManager path services/ → utils/
- tts-generation.mdx: ModelConfig example uses field(default_factory=...) — mutable default would raise at runtime
- tts-generation.mdx: "1080p samples" → "on CUDA" (1080p is video, not audio)
- PROJECT_STATUS.md: replace ASCII architecture diagram with prose (matches no-ASCII-art rule)

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(app): guard against undefined engine in FloatingGenerateBox preset check

form.getValues('engine') returns string | undefined; Set<string>.has()
rejects undefined under strict mode. Added a truthy guard before the
preset lookup.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 21:06:06 -07:00
da6070155e landing: three more tutorials, mobile navbar + hero CTA fixes (#483)
- Add three tutorial cards (Danish Sofi, StinkyScrublet, mikbes)
- Navbar: switch parent to flex/justify-between on mobile (grid on sm+),
  unhide Donate button so both CTAs sit on the right, matching desktop
- Hero CTAs: keep Download and GitHub side-by-side on mobile instead of
  stacking vertically

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 19:21:46 -07:00
3c1e8512b9 fix(build): install mlx-audio/mlx-lm with --no-deps to bypass transformers 5.x conflict (#482)
The previous fix (#481) capped transformers at 4.57.6 in requirements-mlx.txt,
but pip's clean resolver in CI can't satisfy that alongside mlx-audio>=0.3.1
(declares `transformers==5.0.0rc3` or `>=5.0.0`) — it backtracks through every
transformers and tokenizers version and exits with `ResolutionImpossible`.

The dev install worked only because mlx-audio 0.4.1 was already present, so
pip never tried to re-resolve.

mlx-audio 0.4.1 + mlx-lm 0.31.1 both declare transformers>=5.x but the API
surface we actually use works fine on 4.57.x in practice (verified across all
engines in dev). Install both --no-deps to bypass the resolver; transitive
runtime deps (huggingface_hub, librosa, numpy, numba, pyloudnorm, etc.) are
already pulled in by requirements.txt.

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 17:43:31 -07:00
bf58750447 fix(build): pin transformers in MLX requirements to prevent 5.x upgrade (#481)
mlx-audio depends on `transformers` with no upper bound. Installing
requirements-mlx.txt after requirements.txt lets pip upgrade transformers
past the 4.57.x cap to 5.x, which breaks three engines in the frozen MLX
bundle:

- qwen-custom-voice: `check_model_inputs` was rewritten to take `func` as
  positional, so `@check_model_inputs()` factory calls fail with
  `TypeError: missing 1 required positional argument: 'func'`
- tada-1b: `PretrainedConfig.__init_subclass__` now applies `@dataclass`,
  which rejects tada's `strides: list = []` mutable default
- luxtts: Whisper init hits `AssertionError` in `torch._refs.normal_`

Restating the same constraint here keeps mlx-audio's transformers
dependency from quietly winning the resolver.

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 17:05:36 -07:00
Jamie PineandGitHub 2d56309bdd Change 'About' link text to 'Models' 2026-04-18 16:46:23 -07:00
James Pine 0445be295c tests and better website 2026-04-18 16:19:12 -07:00
James Pine 8d550a5f7c Bump version: 0.4.0 → 0.4.1 2026-04-18 15:15:58 -07:00
Esteban FraccasciaandGitHub 795bd54381 fix(linux): use pactl to detect PipeWire/PulseAudio monitor for system audio capture (#457)
cpal 0.15 uses ALSA as its Linux backend, which does not expose
PulseAudio/PipeWire monitor sources. The previous approach searched
for 'monitor' in cpal device names, which never matched on most
Linux systems, silently falling back to the microphone input.

This fix:
- Detects the correct monitor source via 'pactl get-default-sink'
  and 'pactl list short sources'
- Sets PULSE_SOURCE env var before cpal initialization so PulseAudio's
  ALSA plugin routes the default input through the monitor
- Preserves the original name-based search as fallback when pactl is
  unavailable
- No new dependencies added

Tested on PipeWire 1.0.5 with Realtek ALC897 (HD-Audio Generic).
2026-04-18 03:15:05 -07:00
a6ab5f3858 Add initial frontend quality gates and TS hardening (#418)
Co-authored-by: Erion De Andrade <[email protected]>
2026-04-18 03:14:43 -07:00
9d7e4a417e fix(api-client): declare moved + errors on migrateModels response type (#470)
ModelManagement.tsx reads migrationResult.moved (added in #433) but
apiClient.migrateModels() was typed as returning only { source, destination }.
The backend actually returns { moved: int, errors: list[str], source, destination }
(backend/routes/models.py:140, 168). Widen the TS return type so the check
typechecks under the new CI gate from #418.

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-04-18 03:14:08 -07:00
882cabc7d2 fix: warn user when no models to migrate during storage change (#433)
When user attempts to change model storage location with no models
downloaded, the migration API returns moved=0 early. Previously the UI
would still call setCustomModelsDir() and restart the server, causing
unexpected behavior (hang/connection lost).

This change checks migrationResult.moved === 0 and shows a helpful
toast message instead of proceeding with the storage change.

Fixes: #426

Co-authored-by: fuleinist <[email protected]>
2026-04-18 03:13:06 -07:00
9c76b5de2c docs: clarify paralinguistic tag support in quick start (#450)
Co-authored-by: txhno <[email protected]>
2026-04-18 03:12:46 -07:00
Cocoon-BreakandGitHub 4560b7378a fix: delete version rows and files in delete_generations_by_profile (Closes #446) (#447)
Signed-off-by: Cocoon-Break <[email protected]>
2026-04-18 03:12:39 -07:00
高巨龙andGitHub abd9943430 Fix migration dialog hanging when no models are present (#439)
When migrating model path with an empty cache, backend returned early without emitting migration completion SSE, causing frontend overlay to hang. This patch emits complete status for empty migrations.
2026-04-18 03:12:32 -07:00
c8cb12f1bc fix(build): repair frozen-binary imports for kokoro, chatterbox-multilingual, scipy, transformers (#438)
* fix(build): bundle kokoro source files for transformers runtime introspection

transformers opens .py source files at runtime to check attention/MoE
implementation via regex (e.g. _can_set_attn_implementation). PyInstaller's
--hidden-import only bundles .pyc bytecode, so kokoro/modules.py was missing
from the bundle causing a FileNotFoundError on Kokoro model load.

Switch from individual --hidden-import entries to --collect-all kokoro in both
build_binary.py and voicebox-server.spec. The kokoro package is 172K so no
meaningful bundle size impact.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(build): use SPECPATH for runtime hook instead of hardcoded absolute path

The linter expanded runtime_hooks=[] to an absolute /Users/... path which
would break CI and other dev machines. Use os.path.join(SPECPATH, ...) to
mirror the relative approach in build_binary.py.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(build): runtime hook to work around PyInstaller + Python 3.12 import breakages

Four distinct bundling-specific crashes blocked Kokoro and Qwen CustomVoice
from loading in the frozen binary:

1. torch._dynamo import triggered via class-body decorators
   (@torch._dynamo.allow_in_graph on PreTrainedModel,
   @torch.compiler.disable in flex_attention) pulls in torch._numpy._ufuncs
   which crashes on module load with NameError: name 'name' is not defined.

2. AlbertModel (Kokoro) triggers @auto_docstring -> modeling_auto ->
   GenerationMixin -> candidate_generator -> sklearn -> scipy, which hits
   the same class of bug in scipy.stats._distn_infrastructure (NameError:
   name 'obj' is not defined).

3. AutoModel (Qwen) pulls the same sklearn -> scipy chain directly.

4. librosa (required by most TTS engines) -> scipy.signal -> scipy.stats
   hits the _distn_infrastructure crash regardless of the transformers
   stubs above.

The root cause of (1) and (4) is that PyInstaller's frozen importer runs
module-level `for X in [<list-comp using dir()>]:` loops with an empty
iterable, leaving the loop variable unbound. Trailing `del obj` / unrelated
references then crash.

Fix: a single runtime hook (pyi_rth_torch_compiler_disable.py) installs:

- sys.modules stubs for torch._dynamo and torch._dynamo.config, plus a
  meta-path finder for torch._dynamo.* submodules — voicebox never uses
  torch.compile/dynamo for inference, so a permissive no-op stub (callable
  as decorator, falsey as predicate, context-manager-safe for
  TransformGetItemToIndex) is drop-in safe.
- meta-path finder stubs for transformers.utils.auto_docstring and
  transformers.generation.candidate_generator — both import-chain
  short-circuits; docstrings and speculative decoding aren't used for TTS.
- meta-path finder for scipy.stats._distn_infrastructure that reads the
  real .py source via the wrapped loader's get_source(), replaces the
  bundling-broken `del obj` with `globals().pop('obj', None)`, and
  compile+exec's the patched source. This keeps the real scipy module
  intact so librosa and everything downstream works normally.

Supporting changes:

- backend/pyi_hooks/hook-scipy.stats._distn_infrastructure.py sets
  module_collection_mode = "pyz+py" so the .py source is actually in the
  bundle for the runtime patcher to read.
- build_binary.py and voicebox-server.spec register the runtime hook and
  the new hooks dir.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(build): force transformers torch<2.6 mask path and bundle spacy_pkuseg

- patch transformers.masking_utils to set _is_torch_greater_or_equal_than_2_6
  = False, forcing sdpa_mask_older_torch and avoiding the vmap .item() crash
  that breaks Qwen CustomVoice generation (our torch._dynamo stub can't
  reproduce TransformGetItemToIndex's graph transform).
- add PyInstaller hook to bundle transformers.masking_utils .py source so the
  runtime finder can source-patch it.
- --collect-all spacy_pkuseg so Chatterbox Multilingual can load its Chinese
  segmenter (dicts/default.pkl + native .so extensions).
- add per-finder install diagnostics + _HOOK_VERSION marker to make future
  bundle-only regressions easier to triage.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

* fix(build): pass PyInstaller hook paths relative so .spec is portable

Absolute paths ended up in the auto-regenerated voicebox-server.spec
because build_binary.py prefixed every --runtime-hook and
--additional-hooks-dir with str(backend_dir / ...). That broke builds
on any machine whose checkout wasn't at /Users/jamie/... and anyone
invoking pyinstaller voicebox-server.spec directly.

os.chdir(backend_dir) already runs before PyInstaller (same reason
server.py works as a bare filename), so the backend_dir prefix is
unnecessary. Drop it so the generated spec references pyi_hooks/,
pyi_rth_numpy_compat.py, pyi_rth_torch_compiler_disable.py as repo-
relative paths.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-18 03:12:13 -07:00
Andrew BarnesandGitHub 54a3bf322e fix: add generation cancellation flow (#444) 2026-04-18 02:51:39 -07:00
476abe07fc fix(paths): strip legacy "data/" prefix when resolving stored paths (#440)
0.3.0 sometimes stored relative media paths with the data-dir name baked in
(e.g. "data/profiles/<uuid>/sample.wav"). resolve_storage_path joined those
directly with _data_dir, producing "<data_dir>/data/profiles/..." — a
spurious double nest that breaks file reads after upgrading to 0.4.0.

The 0.4.0 startup migration didn't catch it because resolve_storage_path
produced the buggy double-nested path, to_storage_path saw "data" at the
first (legitimate) index, and the normalized value matched the stored value
so the row was skipped.

Strip any leading "data/" component before joining. This unblocks runtime
reads and lets _normalize_storage_paths rewrite the affected rows on next
startup — no manual migration needed.

Fixes "No such file or directory: '<data_dir>/data/profiles/...'" and
associated 404s on GET /audio/<id> after upgrading from 0.3.0 to 0.4.0.

Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-17 17:53:11 -07:00
James PineandClaude Opus 4.6 67bf8e906a docs/landing: update for 0.4.0 — new engines, GPU docs, donate button, voice docs restructure
Docs:
- Add gpu-acceleration.mdx (all 9 platform/GPU combos, CUDA backend swap, Blackwell, XPU, troubleshooting)
- Add preset-voices.mdx (Kokoro 50 voices, Qwen CustomVoice 9 voices, instruct mode docs)
- Restructure voice-cloning.mdx to cover all 5 cloning engines with comparison table
- Restructure creating-voice-profiles.mdx around cloned vs preset workflows
- Update voice-profiles.mdx schema with voice_type discriminator, preset/design columns

Landing:
- Add 3 new engine cards (Qwen CustomVoice, HumeAI TADA, Kokoro) to Multi-Engine section
- Add Donate button (Buy Me a Coffee) to navbar and footer
- Add DONATE_URL constant

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 19:51:43 -07:00
James Pine 625e1ba549 Bump version: 0.3.1 → 0.4.0 2026-04-16 03:16:06 -07:00
James PineandClaude Opus 4.6 cfe6770639 style: apply biome format to drifted authored source
Catches format drift that accumulated across 13 authored files in
app/src and docs/. Auto-generated artifacts (tauri/src-tauri/gen,
docs/openapi.json, docs/cli.json, app/src/lib/api) were left alone
since the build regenerates them on each run — baking their formatted
state into git just causes churn next build.

No behavioral changes. Trailing commas, line wrapping, and indentation
only.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 03:13:45 -07:00
James PineandClaude Opus 4.6 00452b51a8 style(changelog): make entry version headings bigger in settings UI
The in-app changelog viewer rendered each entry's version number at the
same size as body text (text-sm font-medium), so visually there was no
clear anchor for where one release's notes ended and the next began.

Bump the version heading to text-xl font-semibold tracking-tight and
widen the bottom margin so each release reads as a proper section
header.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 03:12:09 -07:00
James PineandClaude Opus 4.6 106aec46a8 feat(generate): restore instruct toggle in floating generate box (Qwen CustomVoice)
Before 0.4 every engine was a cloning model, so the instruct UI in the
floating generate box applied the same way everywhere. Commit 3187344
hid the instruct toggle because the mix of new engines landing in 0.4
made it unclear which ones honored the kwarg. With Qwen CustomVoice
now shipping as the only engine actually tuned for instruct-style
control, bring the button back — conditionally, and only for that
engine.

Changes:
  • FloatingGenerateBox: SlidersHorizontal toggle button appears left
    of Generate when the box is expanded AND engine is
    qwen_custom_voice. Clicking it reveals an additive instruct
    textarea below the main text field (not a modal swap like the old
    version). State persists across engine switches so the toggle
    remembers its last position.
  • GenerationForm: narrow the instruct FormField's conditional from
    `qwen || qwen_custom_voice` to just `qwen_custom_voice`.
  • useGenerationForm: narrow supportsInstruct for the same reason.
    Base Qwen3-TTS accepts the kwarg but the model itself doesn't honor
    it — only CustomVoice was trained for instruction-based style
    control.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 03:09:55 -07:00
James PineandClaude Opus 4.6 c9e5c5d9a7 fix: clean up scroll effect timers and fix disabled+selected card toggle
- Add cleanup for requestAnimationFrame and setTimeout in scroll effect
  to prevent stale DOM writes on unmount or rapid selection changes
- Fix disabled+selected card click: bounce the selection to re-trigger
  the engine auto-switch instead of deselecting

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 02:56:45 -07:00
James PineandClaude Opus 4.6 48cd1f369a feat: gray out unsupported profiles instead of filtering, auto-switch engine on selection
- Show all voice profiles with unsupported ones grayed out (opacity) instead of hidden
- Clicking a grayed-out profile selects it and auto-switches the engine to a compatible one
- Sort supported profiles first, with info tip about compatibility at the bottom
- Scroll to selected profile after engine/sort changes with safe margin
- Fix engine desync on tab navigation by initializing form engine from store

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 02:56:45 -07:00
James PineandClaude Opus 4.6 2bfe400457 feat(skills): add triage-prs skill for pre-release PR speedruns
Immortalizes the workflow used to clear the open-PR backlog before
0.4.0: classify every open PR into merge / candidate / supersede /
defer tiers, write a working triage doc, then run the merge loop —
rebasing where needed, merging in batches, applying post-merge
follow-ups, and closing superseded PRs with credit.

Captures the gotchas that matter most:
  • Never review a stale branch via `git diff main..HEAD` — it shows
    every intermediate main commit as a deletion and makes a 3-line
    PR look like a 700-line revert
  • Always rebase before squash-merging; GitHub's squash computes
    diff(PR-head, merge-base), so a stale branch will revert
    in-between work
  • Route-ordering, weak-framework linking, dependency floors, !Send
    audio types, and why PyTorch nightly isn't shippable

Paired with draft-release-notes and release-bump: triage → draft →
bump.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 02:22:57 -07:00
0aa19a9994 feat(history): add "Clear failed" button to wipe failed generations (#412)
When the model wasn't loaded, the app was closed mid-run, or a
generation otherwise errored out, the resulting "Failed" rows
accumulate in history and there was no way to remove them in bulk —
individual delete was the only option.

Adds a header row above the history list (only rendered when at
least one failed generation is present) with a "Clear failed" button
that opens a confirmation dialog, then calls a new
DELETE /history/failed endpoint which sweeps all status='failed'
rows (plus their version files / audio files on disk).

Closes jamiepine/voicebox#410

Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-04-16 02:12:30 -07:00
73170d0e92 feat(health): warn when GPU arch isn't supported by PyTorch build
Applies the compatibility-checker portion of #367. Adds a
check_cuda_compatibility() helper that compares the current device's
compute capability against torch.cuda._get_arch_list() and returns a
human-readable warning if the PyTorch build doesn't support it.

Wired into three places:
  • HealthResponse gains a gpu_compatibility_warning field so clients
    can surface the issue in the UI
  • Startup logs the warning as WARN level
  • _get_gpu_status() appends "[UNSUPPORTED - see logs]" to the GPU
    label shown in settings

Skipped #367's other half — the switch from stable to nightly cu128
wheels across release.yml, build_binary.py, and justfile. That's
redundant with #401's TORCH_CUDA_ARCH_LIST=...12.0+PTX approach and
would introduce non-deterministic builds from shifting nightly
releases.

Co-Authored-By: nyzxor <[email protected]>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 02:11:23 -07:00
James PineandClaude Opus 4.6 0317626677 fix(qwen): unify HF cache dir to avoid split cache on Windows
Applies the cache_dir portion of #218. On Windows local setups, model
assets can split between .hf-cache/hub and .hf-cache/transformers when
Qwen3TTSModel.from_pretrained doesn't explicitly pin the cache root —
speech_tokenizer and preprocessor_config.json then fail to resolve
during load, causing 500s at generation time.

Routes both HF Hub and Transformers through hf_constants.HF_HUB_CACHE.

Skipped the torch_dtype= → dtype= rename from #218: transformers 4.36
(our minimum) doesn't accept the dtype alias, only 4.46+. Once we bump
the minimum we can make that change.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 02:08:59 -07:00
a5d5c780c2 fix: avoid ScreenCaptureKit launch crash on macOS 11 (#424)
Co-authored-by: txhno <[email protected]>
2026-04-16 01:58:29 -07:00
James PineandClaude Opus 4.6 7184a25e44 fix(watchdog): clear stale .keep-running sentinel on startup
Follow-up to #402. The sentinel is only removed inside the grace-period
"sentinel found" branch. When the HTTP /watchdog/disable request wins
the race (normal case on macOS/Linux, occasional on Windows), the
_watchdog_disabled=True check returns first and the sentinel is left on
disk indefinitely.

If a later session spawns a fresh server and the user exits without
"keep running", the new watchdog would find that stale sentinel during
its grace period and keep the server alive against user intent.

Wipe any pre-existing sentinel when the watchdog starts so only signals
written during this session's lifetime can influence grace-period
decisions.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 01:57:05 -07:00
479bc7fc5e fix: reliably keep server alive after GUI close on Windows (#402)
The HTTP /watchdog/disable request races with process exit on Windows,
causing the watchdog to kill the server before the request arrives.

Added a .keep-running sentinel file as a reliable fallback:
- Tauri writes the file to data_dir before sending the HTTP request
- The watchdog checks for it during the grace period after detecting
  parent death
- The file is removed after being read to avoid stale state

This approach works regardless of HTTP timing because file writes
complete synchronously before the Tauri process exits.

Fixes #372

Co-authored-by: Matt Van Horn <[email protected]>
2026-04-16 01:56:30 -07:00
Cocoon-BreakandGitHub 3e7727d1d2 fix: keep cpal Stream alive until playback completes (Closes #404) (#405)
The cpal Stream was created and play() called but then immediately
dropped when play_to_device() returned. When a cpal Stream is dropped,
audio output stops immediately. This caused silent playback.

Fix: add a spin-wait loop that holds the Stream in scope until all
samples have been consumed (or stop_flag is set).
2026-04-16 01:54:31 -07:00
JunghwanandGitHub be7c0cec12 fix: add asyncio.Lock to prevent concurrent CUDA downloads (#428)
* fix: add asyncio.Lock to prevent concurrent CUDA downloads

The startup auto-update task and the manual download endpoint can both
invoke download_cuda_binary() concurrently. Without mutual exclusion,
both coroutines write to the same temp file path, corrupting the
download. The progress-manager status check is a TOCTOU race because
the status is not set until after several synchronous checks complete.

Add a module-level asyncio.Lock acquired at the top of
download_cuda_binary() so only one download can proceed at a time.

* fix: fast-reject duplicate CUDA download when lock is held

Address CodeRabbit review feedback: check _download_lock.locked()
before awaiting the lock so concurrent callers return immediately
instead of queueing behind the first download. This prevents the
route handler from returning "started" to multiple callers when only
one download actually proceeds.
2026-04-16 01:51:21 -07:00
c9d8142a78 feat: add Blackwell GPU (sm_120) CUDA support (#401)
Set TORCH_CUDA_ARCH_LIST in the CUDA build step to include 12.0+PTX
for forward compatibility with Blackwell GPUs (RTX 5070 Ti, 5080, etc).

Pre-built PyTorch cu128 wheels only ship native kernels for sm_80/86/89/90.
Without this, Blackwell GPU users get "no kernel image is available for
execution on the device" at runtime.

Fixes #386
Related: #395, #396, #399, #400

Co-authored-by: Matt Van Horn <[email protected]>
2026-04-16 01:51:18 -07:00
13ba5f1aa6 fix: prevent intermittent clip splitting failures (#403)
Two changes to address the race condition causing "Failed to split clip":

Backend (stories.py): Added with_for_update() to the item query in
split_story_item so concurrent requests for the same clip are
serialized via a row lock instead of racing.

Frontend (StoryTrackEditor.tsx): Guard handleSplit with
splitItem.isPending to prevent rapid double-clicks from firing
multiple mutations before the first completes.

Fixes #366

Co-authored-by: Matt Van Horn <[email protected]>
2026-04-16 01:51:15 -07:00
9a3c307c75 fix(history): populate status/error/engine fields from DB row (#394)
* fix(history): populate status/error/engine/model_size/is_favorited from DB

GET /history/{generation_id} was constructing HistoryResponse without
passing status, error, engine, model_size, or is_favorited from the
DB row. Since HistoryResponse.status defaults to "completed" in the
Pydantic model (models.py:141), this endpoint returned
status="completed" for every generation regardless of the actual DB
state — including jobs still in "loading_model" or "generating", and
even "failed" jobs.

This breaks any client polling /history/{id} for job completion:
the API lies about the status, so the only trustworthy success
signal becomes `audio_path` being non-empty. All other fields left
at their model defaults were similarly masked.

Fix: pass all fields through from the DB row, matching the pattern
used elsewhere in the codebase. The DB model (Generation in
database/models.py) already has all these columns.

* fix(history): apply NULL fallbacks to match list endpoint

Align the defensive mappings with services/history.py:206-223 so
both the single-item and list history endpoints handle legacy rows
with NULL status/engine/is_favorited identically. Without this,
HistoryResponse's non-Optional str/bool fields would raise a
pydantic ValidationError (500) on any row where these columns are
NULL — possible from direct SQL updates or past migrations.

Addresses review feedback on PR #394.

---------

Co-authored-by: malletfils <[email protected]>
2026-04-16 01:51:12 -07:00
JunghwanandGitHub 1da16cfc57 fix: harden voice prompt cache loading and SPA path guard (#429)
Two small safety improvements:

1. Voice prompt cache (cache.py): add weights_only=True to torch.load()
   so cached .prompt files are loaded using the safe unpickler instead of
   the unrestricted pickle deserializer. This follows the PyTorch 2.6+
   best practice of opting in to safe loading for all torch.load() calls.

2. SPA catch-all (app.py): replace str.startswith() path guard with
   Path.is_relative_to(). The string prefix check passes for sibling
   paths like /app/frontend_evil/ that share the /app/frontend prefix.
   is_relative_to() correctly tests directory containment.
2026-04-16 01:49:19 -07:00
Luis SambranoandGitHub a1807be04d fix(deps): relax torch requirement for macOS x86_64 compatibility (#416) 2026-04-16 01:49:16 -07:00
Khaled SolimanandGitHub fdba18e9ee fix: resolve ModuleNotFoundError by using relative import for utils (#384) 2026-04-16 01:49:13 -07:00
MaxandGitHub 07a845cece Add NUMBA_CACHE_DIR environment variable (#425) 2026-04-16 01:49:10 -07:00
James PineandClaude Opus 4.6 615d604ceb fix(numpy-compat): raise on unknown dtype + add fp16/complex
Follow-up to #361. The original fallback silently mapped unknown numpy
dtypes to torch.float32, which would reinterpret the memcpy'd bytes in
the wrong dtype and corrupt data (e.g. fp16 tensors from some TTS
engines) rather than erroring loudly.

- Hoist dtype_map out of the inner function so it's built once
- Add float16, complex64, complex128 mappings
- Raise TypeError on unknown dtype instead of silent float32 fallback

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 01:47:22 -07:00
a383ff6863 fix: torch.from_numpy crash with numpy 2.x in frozen binary (#361)
torch is compiled against numpy 1.x. numpy 2.x changed the ABI version
returned by PyArray_GetNDArrayCVersion() (0x01000009 → 0x02000000), so
torch's is_numpy_available() always returns False and torch.from_numpy()
raises RuntimeError. This causes TTS generation to fail with:

  ValueError: Unable to create tensor, you should probably activate
  padding with 'padding=True'

Two fixes:

1. Pin numpy<2.0 in requirements.txt so new builds bundle a compatible
   numpy version. (The existing comment already flagged this intention
   but the upper bound was never added.)

2. Add a PyInstaller runtime hook (pyi_rth_numpy_compat.py) that installs
   a ctypes memmove fallback for torch.from_numpy() at startup. Runtime
   hooks run after FrozenImporter is registered so frozen torch is
   importable. The fallback catches RuntimeError from the C-level ABI
   check and copies the numpy array into a new tensor via raw memory copy,
   bypassing the check entirely. This is a belt-and-suspenders fix that
   works regardless of the bundled numpy version.

Co-authored-by: aimaaaimaa <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
2026-04-16 01:46:40 -07:00
Jamie PineandGitHub 75abbb02c3 Merge pull request #344 from pandego/fix/308-docker-compose-startup
fix: include changelog in docker web build
2026-03-26 23:06:47 -07:00
Jamie PineandGitHub b49f14a814 Merge pull request #319 from jamiepine/fix/startup-and-server-switch
fix: GUI startup with external server + data refresh on server switch
2026-03-26 23:06:29 -07:00
Jamie PineandGitHub 05686efbfd Merge pull request #345 from ArfianID/fix/backend-import-error
Fix: "Failed to Save" preset error by resolving backend import path resolution
2026-03-22 09:45:25 -07:00
Arfian e2c03fef9a Fix: move lazy imports to top-level and use absolute paths to resolve ModuleNotFoundError in production 2026-03-22 22:29:25 +07:00
pandego 4347eaed4c fix: include changelog in docker web build 2026-03-22 09:32:32 +01:00
James Pine 60aac279ce fix: address PR #319 review feedback — health validation, error handling, queryClient decoupling
- Rust: Replace fragile body.contains("status") with proper JSON
  deserialization validating status=="healthy", model_loaded (bool),
  and gpu_available (bool) to prevent misidentifying non-Voicebox services

- Frontend: Validate health response has Voicebox-specific fields before
  marking server as ready during fallback polling

- Frontend: Discriminate port-in-use errors (poll for external server) from
  real startup failures (missing sidecar, signing issues) — surface errors
  immediately with a startupError state and Retry button in the UI

- Frontend: Set explicit startup-error state when 2-minute polling timeout
  expires so the loading screen shows actionable feedback instead of hanging

- Architecture: Extract QueryClient to standalone side-effect-free module
  (lib/queryClient.ts) to decouple serverStore from React bootstrap entrypoint
2026-03-21 10:24:15 -07:00
James Pine 8b1c7552be Merge remote-tracking branch 'origin/fix/startup-and-server-switch' into pr-319 2026-03-21 10:18:45 -07:00
Jamie PineandGitHub 9a955a77d2 Merge pull request #320 from jamiepine/feat/intel-xpu-support
feat: Intel Arc (XPU) GPU support
2026-03-21 08:39:51 -07:00
Jamie PineandGitHub c18591c0c3 Merge pull request #318 from jamiepine/fix/offline-model-loading
fix: force offline mode when loading cached models (Qwen TTS & Whisper)
2026-03-21 08:38:08 -07:00
Jamie PineandGitHub ea3469f2dc Merge pull request #332 from nicoschtein/patch-1
Fix links in Get Started section of index.mdx
2026-03-21 08:37:00 -07:00
James Pine b108bb1cb1 fix: store media paths relative to data dir 2026-03-20 15:06:07 -07:00
Nicolas SchteinschraberandGitHub 8b796bc6b4 Fix links in Get Started section of index.mdx
Updated links in the Get Started section for correct paths.
2026-03-20 13:58:53 -03:00
James Pine e6f419cd70 fix: show all engines in floating generator 2026-03-19 19:52:08 -07:00
James Pine 72c13fd3fc fix: enforce preset profile engine compatibility 2026-03-19 19:51:53 -07:00
James Pine 4e0c731db8 feat: add Qwen CustomVoice preset engine 2026-03-19 19:48:50 -07:00
James Pine d70b878b71 fix: tighten kokoro profile handling 2026-03-19 19:32:49 -07:00
Jamie PineandGitHub a71011741d Merge pull request #325 from jamiepine/feat/kokoro-engine
feat: Kokoro 82M TTS engine + voice profile type system
2026-03-19 19:21:15 -07:00
James Pine d6f48ace3e Mirror the regular /generate endpoint behavior more closely 2026-03-19 16:11:38 -07:00
James Pine 0fc2192204 fix: resolve relative paths using configured data dir, not CWD 2026-03-19 10:37:11 -07:00
James Pine 9e726ad048 fix: remove engine dropdown filtering — profile grid handles it 2026-03-19 10:14:33 -07:00
James Pine 3584283d84 feat: Kokoro 82M TTS engine + voice profile type system
Add Kokoro-82M as a new TTS engine — 82M params, CPU realtime, 8 languages,
Apache 2.0. Unlike cloning engines, Kokoro uses pre-built voice styles, which
required a new profile type system to support non-cloning engines cleanly.

Kokoro engine:
- New kokoro_backend.py implementing TTSBackend protocol
- 50 built-in voices across en/es/fr/hi/it/pt/ja/zh
- KPipeline API with language-aware G2P routing via misaki
- PyInstaller bundling for misaki, language_tags, espeakng_loader, en_core_web_sm

Voice profile type system:
- New voice_type column: 'cloned' | 'preset' | 'designed' (future)
- Preset profiles store engine + voice ID instead of audio samples
- default_engine field on profiles — auto-selects engine on profile pick
- Create Voice dialog: toggle between 'Clone from audio' and 'Built-in voice'
- Edit dialog shows preset voice info instead of sample list for preset profiles
- Engine selector locks to preset engine when preset profile is selected
- Profile grid filters by engine — shows Kokoro voices when Kokoro selected
- Custom empty state when no preset profiles exist for selected engine

Bug fixes:
- Fix relative audio paths in DB causing 404s in production builds
- config.set_data_dir() now resolves to absolute paths
- Startup migration converts existing relative paths to absolute

Also updates PROJECT_STATUS.md and tts-engines.mdx developer guide.
2026-03-19 10:09:48 -07:00
Jamie PineandGitHub e4def9365f Merge pull request #321 from liorshahverdi/fix/delete-failed-generations-292
fix/allows deletion of failed generations 292
2026-03-19 09:36:55 -07:00
James Pine 707046237c fix: complete Intel XPU support — device-aware seeding, GPU status reporting, and setup detection
Address CodeRabbit review feedback and user-reported GPU acceleration failure:

- Use shared manual_seed() in chatterbox, chatterbox_turbo, and luxtts
  backends so XPU (and future accelerators) get proper device seeding
- Add XPU branch to _get_gpu_status() so startup log reports Intel Arc
  GPUs instead of 'None (CPU only)'
- Add XPU VRAM reporting and correct backend_variant fallback in the
  /health endpoint
- Switch justfile GPU detection from Get-WmiObject to Get-CimInstance,
  simplify the Arc regex to match 'Arc' (not 'Intel.*Arc'), log
  detected GPUs, and print manual install instructions on miss

Resolves the root cause where IPEX was silently not installed due to
WMI detection failure, causing CPU-only fallback on Intel Arc systems.
2026-03-18 17:01:12 -07:00
Lior Shahverdi 12ed2d51ce Adds a trash icon button alongside the existing retry button for
failed generations, giving users a way to clean up failed entries
  without having to retry them first.
2026-03-18 15:44:37 -04:00
James Pine 83ebababe7 feat: add Intel Arc (XPU) GPU support across all backends
Auto-detect Intel Arc GPUs during Windows setup and install PyTorch
with XPU support + intel-extension-for-pytorch. Enable allow_xpu=True
on all TTS backends (Chatterbox, Chatterbox Turbo, Hume TADA, LuxTTS)
that previously only supported CUDA. Add shared empty_device_cache()
and manual_seed() helpers in base.py to handle XPU memory management
and reproducible seeding alongside CUDA.
2026-03-18 11:24:51 -07:00
James Pine eb5869e59f fix: GUI startup with external server + data refresh on server switch
Two fixes for issue #312:

1. GUI stuck on loading screen when backend is already running externally
   (e.g. via python/uvicorn/Docker):

   - Rust: add HTTP health check fallback when the process on the port
     doesn't have 'voicebox' in its name. If /health responds with a
     valid Voicebox response, reuse the server instead of erroring.
   - Frontend: when startServer() fails, fall back to polling the
     health endpoint every 2s instead of permanently blocking.

2. No data refresh when switching server URLs in settings:

   - serverStore.setServerUrl() now invalidates all React Query caches
     when the URL actually changes, so profiles/history/models/stories
     are re-fetched from the new server.
   - Export queryClient from main.tsx for store-level cache invalidation.

Fixes #312
2026-03-18 10:59:59 -07:00
James Pine 2e95b7c5d8 fix: force offline mode when loading cached models (Qwen TTS & Whisper)
Qwen TTS and Whisper Base make network calls to HuggingFace even when
model weights are fully cached locally, because from_pretrained()
defaults to local_files_only=False. This causes failures for offline
users.

Add a reusable force_offline_if_cached() context manager that sets
HF_HUB_OFFLINE=1 during model loading when is_model_cached() is True.
Applied to all four affected load paths:

- PyTorchTTSBackend (Qwen TTS)
- PyTorchSTTBackend (Whisper)
- MLXTTSBackend (refactored from inline implementation)
- MLXSTTBackend (previously unprotected)

Closes #82
2026-03-18 10:31:30 -07:00
Jamie PineandGitHub ffc1b54812 Merge pull request #316 from jamiepine/fix/cuda-cu128-upgrade
Upgrade CUDA backend from cu126 to cu128, fix GPU settings UI
2026-03-18 07:58:12 -07:00
James Pine fc5ed1ff40 upgrade CUDA backend from cu126 to cu128 and fix GPU settings UI
Upgrade CUDA toolkit from 12.6 (cu126) to 12.8 (cu128) for proper
RTX 50-series (Blackwell) GPU support. Users with RTX 5070/5080/5090
were reporting CUDA detection failures with cu126.

Also fix the GPU Acceleration settings panel where the 'Switch to CPU
Backend' button was unreachable — it was inside a conditional block
that required !isCurrentlyCuda, making it impossible to switch back
to CPU once running on CUDA.

Closes #315
2026-03-18 07:47:39 -07:00
Jamie PineandGitHub c9f38dd496 Merge pull request #305 from jamiepine/fix/qwen-tts-pyinstaller-source-files
fix: bundle qwen_tts source files in PyInstaller build
2026-03-17 09:24:42 -07:00
James Pine 58b19e4e9f fix: bundle qwen_tts source files in PyInstaller build
Replace --collect-submodules + --collect-data with --collect-all for
qwen_tts. The qwen_tts runtime expects physical .py source files
(e.g. modeling_qwen3_tts.py) under _MEIPASS, which only --collect-all
provides. This is the same pattern used for inflect/typeguard.

Fixes #212
2026-03-17 09:23:30 -07:00
Jamie PineandGitHub 0245c31dba Merge pull request #298 from jamiepine/feat/cuda-libs-addon
feat: split CUDA backend into independently versioned server + libs archives
2026-03-17 09:17:31 -07:00
Jamie Pine 81864e831a fix: always clean up temp archive on failure and fix justfile data dir path
- Wrap download/verify/extract in try/finally so .download-*.tmp is
  always deleted, even on mid-download or extraction failures
- Fix justfile build-server-cuda to use sh.voicebox.app (production path)
2026-03-17 09:15:23 -07:00
Jamie Pine 7bd72ea9f7 Bump version: 0.3.0 → 0.3.1 2026-03-17 07:50:12 -07:00
Jamie Pine f96eae2567 fix: address PR review feedback from CodeRabbit
- Upgrade softprops/action-gh-release@v1 to @v2 (Node 16 EOL)
- Fail-fast on checksum fetch failure instead of extracting unverified archives
- Abort packaging if no NVIDIA files found (prevents empty cuda-libs archive)
- Fix nvidia/ path detection bug (list membership vs substring check)
- Fix justfile Copy-Item nesting (copy contents, not the directory itself)
2026-03-17 06:53:54 -07:00
Jamie Pine 7d53699c96 fix: update build-server-cuda to copy onedir folder instead of single exe 2026-03-17 06:12:30 -07:00
Jamie Pine 28e91ce2c1 chore: add .spec and nul to .gitignore 2026-03-17 04:58:13 -07:00
Jamie Pine 88be097b62 fix: update package_cuda.py for PyInstaller 6.18 layout and remove split_binary.py
- Fix is_nvidia_file() to match NVIDIA DLLs in _internal/torch/lib/
  (PyInstaller 6.18 + torch 2.10 no longer uses nvidia/ subdirectories)
- Remove deprecated split_binary.py (both archives are under 2GB)
- Update torch_compat range to >=2.6.0,<2.11.0
- Update build docs for new dual-archive packaging flow
2026-03-17 04:57:05 -07:00
James Pine 564d787927 feat: split CUDA backend into independently versioned server + libs archives
Switch CUDA builds from PyInstaller --onefile to --onedir and split the
output into two separately versioned archives:

1. Server core (~200-400MB) — versioned with the app, redownloaded on
   every app update
2. CUDA libs (~2GB) — versioned independently (cu126-v1), only
   redownloaded when the CUDA toolkit or torch version changes

This eliminates the ~2.4GB full redownload on every version bump.
After initial setup, most app updates only need ~200-400MB.

Closes #297
2026-03-17 04:04:17 -07:00
James Pine 2c1ee94891 docs: add TADA learnings to TTS engine guide and CUDA libs addon plan
Enrich tts-engines.mdx with patterns discovered during TADA integration:
- Phase 0.2: new greps for @torch.jit.script, torchaudio.load, gated repos
- Phase 3.4: model naming inconsistency warning
- Phase 5.2: TADA shim failure added to lessons table
- Phase 6: four new workaround sections (gated repos, torchcodec,
  torch.jit.script, toxic dependency shim pattern)
- Checklist: four new items matching the new scan patterns
- Remove TADA from upcoming engines (now shipped)

Add CUDA_LIBS_ADDON.md exploring --onedir split to avoid 2.4GB
redownloads on every version bump.
2026-03-17 03:53:40 -07:00
Jamie PineandGitHub e789c937ad Merge pull request #296 from jamiepine/feat/add-tada-tts-engine
Add HumeAI TADA TTS engine (1B English + 3B Multilingual)
2026-03-17 03:47:47 -07:00
James Pine 273483ffcf fix TorchScript error in frozen builds and update docs for TADA
Remove @torch.jit.script from the DAC shim's snake() function —
TorchScript calls inspect.getsource() which fails in PyInstaller
binaries (no .py source files).

Update all user-facing docs: 4 → 5 TTS engines, add TADA row to
every engine comparison table, mark TADA as Shipped in the upcoming
engines list, update architecture diagrams and tech stack tables.
2026-03-17 03:28:58 -07:00
James Pine 5774a168a9 fix TADA 3B model name: tada-3b -> tada-3b-ml 2026-03-17 03:17:53 -07:00
James Pine 6bf40bd2d0 fix tokenizer patch corrupting AutoTokenizer for other engines
Replace the monkey-patch on AutoTokenizer.from_pretrained (which broke
the classmethod descriptor and caused 'Tokenizer not loaded' errors
when loading Qwen after TADA) with two targeted config patches:
- Set AlignerConfig.tokenizer_name to the local ungated tokenizer path
- Pre-load TadaConfig, inject tokenizer_name, pass config= to from_pretrained

No global state is modified; other engines are unaffected.
2026-03-17 03:15:57 -07:00
James Pine 12cda2e090 fix torchcodec error by using soundfile instead of torchaudio.load
torchaudio 2.10+ switched its default audio loading backend to
torchcodec, which isn't installed. Replace torchaudio.load() with
soundfile.read() in create_voice_prompt(). TADA's internal use of
torchaudio.functional.resample() is unaffected (pure PyTorch math,
no torchcodec dependency).
2026-03-17 02:25:05 -07:00
James Pine 7a90290a76 fix gated Llama tokenizer error by redirecting to ungated mirror
TADA hardcodes 'meta-llama/Llama-3.2-1B' as its tokenizer source in
both the Aligner and TadaForCausalLM.from_pretrained(). That repo is
gated and requires accepting Meta's license on HuggingFace.

Monkey-patch AutoTokenizer.from_pretrained during model loading to
redirect Llama tokenizer requests to 'unsloth/Llama-3.2-1B', an
ungated mirror with identical tokenizer files. The patch is scoped
to model loading only and restored immediately after.
2026-03-17 02:22:26 -07:00
James Pine b02ce8e2f3 replace descript-audio-codec with lightweight DAC shim
The real descript-audio-codec package pulls in descript-audiotools,
which transitively requires onnx, tensorboard, protobuf, matplotlib,
pystoi, and other heavy dependencies. onnx fails to build from source
on macOS due to CMake version incompatibility.

TADA only uses Snake1d (a 7-line PyTorch module) from DAC. This commit
adds a shim in backend/utils/dac_shim.py that registers fake dac.*
modules in sys.modules with just the Snake1d class, completely
eliminating the DAC/audiotools dependency chain.
2026-03-17 02:16:33 -07:00
James Pine 4e7772a21d add HumeAI TADA TTS engine (1B English + 3B Multilingual)
Integrates HumeAI's TADA (Text-Acoustic Dual Alignment) speech-language
model as a new TTS engine. TADA uses a novel 1:1 token-audio alignment
that produces coherent speech over long sequences (700s+).

Two model variants:
- tada-1b: English-only, ~4GB, built on Llama 3.2 1B
- tada-3b-ml: 10 languages, ~8GB, built on Llama 3.2 3B

Backend uses the Encoder for voice prompt encoding with caching, and
TadaForCausalLM with flow-matching diffusion for generation. Supports
bf16 inference on CUDA, forces CPU on macOS (MPS compatibility).

Installed with --no-deps due to torch>=2.7 pin conflict; descript-audio-codec
and torchaudio added as explicit sub-dependencies.
2026-03-17 01:55:15 -07:00
James Pine 51fb320b8c readme 2026-03-17 01:24:48 -07:00
James Pine 8ac202aa58 docs for adding new engines 2026-03-17 01:13:30 -07:00
Jamie Pine ac68052945 create stub resource files when actool output is missing
Older Xcode versions don't produce Assets.car from .icon assets.
Fall back to empty stubs for all platforms so the bundler succeeds.
2026-03-17 01:07:54 -07:00
Jamie Pine e601fd2ca4 generate icon assets at build time instead of tracking them
build.rs now generates voicebox.icns via sips + iconutil alongside the
existing actool Assets.car compilation. On non-macOS, empty stub files
are created so Tauri's resource bundler doesn't fail on missing paths.
2026-03-17 00:51:12 -07:00
Jamie Pine 7b25e0ba0b Bump version: 0.2.3 → 0.3.0 2026-03-17 00:25:56 -07:00
Jamie PineandGitHub a6817cd082 Merge pull request #295 from jamiepine/fix/misc-bugs
fix: batch of bug fixes from issue tracker
2026-03-17 00:08:17 -07:00
Jamie Pine df50b8a925 add --force-reinstall --no-deps to torchaudio CUDA install 2026-03-17 00:07:45 -07:00
Jamie Pine a672ac5279 remove voicebox.icns from tracking and add to gitignore 2026-03-17 00:07:19 -07:00
Jamie Pine d35e6f0cc5 fix sample upload blocking the event loop and causing server timeouts
Move audio validation and saving to thread pool so librosa/ffmpeg decoding
doesn't block the async event loop. Combine validate + load into a single
pass to avoid decoding the file twice. Add 50 MB upload limit and chunked
reads to prevent unbounded memory allocation.

Closes #278
2026-03-16 23:29:18 -07:00
Jamie Pine b1069b4521 upgrade CUDA backend build from cu121 to cu126
cu121 only ships kernels up to SM 9.0 (Ada Lovelace). RTX 50-series
(Blackwell, SM 12.0) and RTX 6000 Pro need cu126 which includes SM 12.0
support while remaining backward compatible with older GPUs.

Closes #289
2026-03-16 23:23:55 -07:00
Jamie Pine f9e1aa153d handle client disconnects in SSE and streaming endpoints
Wrap SSE generators with BrokenPipeError/ConnectionResetError handling
so client disconnects during generation status polling, download progress,
or audio streaming don't produce unhandled Errno 32 errors.

Closes #248
2026-03-16 23:17:09 -07:00
Jamie Pine 01800f196f upgrade pip before installing deps in Docker build
Fixes hash mismatch when pip resolves Qwen3-TTS transitive deps.

Closes #286
2026-03-16 23:13:50 -07:00
Jamie Pine 606da1c894 fix generation list not updating on completion
Use refetchQueries instead of invalidateQueries for more reliable history
refresh. Add history refetch to SSE onerror handler so dropped connections
don't leave the list stale. Reset page to 0 in HistoryTable when a pending
generation completes.

Closes #231
2026-03-16 22:54:11 -07:00
Jamie Pine 664178f0cf fix error detail serialization producing [object Object] in error messages
Closes #290
2026-03-16 22:47:01 -07:00
Jamie Pine f1541701fb add model selection and expanded language support to /transcribe endpoint
Closes #233
2026-03-16 22:44:28 -07:00
Jamie PineandGitHub a2adc3b506 Merge pull request #293 from jamiepine/fix/audio-player-freeze
Fix audio player freezing and improve UX
2026-03-16 22:28:39 -07:00
Jamie PineandGitHub 15ba824472 Merge pull request #294 from jamiepine/feat/settings-overhaul
Settings overhaul: routed sub-tabs, server logs, changelog, about page
2026-03-16 13:07:39 -07:00
Jamie Pine 2ad4776a76 fix review feedback: restart race, listener cleanup, stable keys, accessibility 2026-03-16 13:06:57 -07:00
Jamie Pine a8469b39f1 fix about license 2026-03-16 12:31:33 -07:00
Jamie Pine 7dd70a52e4 fix audio player freezing and improve UX
Switch WaveSurfer from MediaElement to WebAudio backend to prevent
WKWebView deadlocks that were freezing the entire Tauri app during
audio playback.

Reuse a single WaveSurfer instance across track changes instead of
destroying and recreating on every URL change, which was exhausting
the browser's AudioContext pool.

Other improvements:
- spacebar play/pause with capture phase to prevent history item activation
- drag-to-seek on waveform with silent scrub to avoid WebAudio popping
- slider always mounted to prevent layout shift during track transitions
- play button fills icon, accent bg when playing, loop button accent bg when active
- fix AudioBars animation getting stuck by keying on mode
- remove focus ring on history items
- sync slider position on pause and during seek
- remove title text from player bar
- thicker cursor (3px)
2026-03-16 12:29:10 -07:00
James Pine 1526f2de26 about page + generation folder open and display 2026-03-16 10:14:47 -07:00
James Pine 2c63dfff25 overhaul settings: split into routed sub-tabs, add server logs, changelog, reusable setting components
- Rename Server tab to Settings with horizontal sub-tab navigation (General, Generation, GPU, Logs, Changelog)
- All sub-tabs are proper routes under /settings/* with /server redirect for backwards compat
- General: connection settings, link cards (docs + discord), API reference card, app updates
- Generation: auto-chunking, crossfade, normalize, autoplay as SettingRow components
- GPU: info card with platform-aware icons (Apple logo for MPS), CUDA management, explainer text
- Logs: real-time server log viewer piped from Tauri sidecar via event system (Tauri-only)
- Changelog: parsed from CHANGELOG.md at build time via Vite virtual module plugin
- New reusable SettingRow/SettingSection components for consistent settings layout
- New Toggle (switch) UI component replacing checkboxes in settings
- Toast viewport now offsets when audio player is open
- Sidebar stays active on settings sub-routes (fuzzy matching)
2026-03-16 09:31:14 -07:00
James Pine e0a798dc0d add release skills, backfill changelog, wire CI to use changelog for GitHub releases
- Backfill CHANGELOG.md from all 17 GitHub releases (was stale at v0.1.0)
- Add draft-release-notes and release-bump agent skills
- Extract release notes from CHANGELOG.md in release CI instead of hardcoded placeholder
- Remove stale PATCH_NOTES.md, mlx-test/, move PROJECT_STATUS to docs/notes
- Reorganize API reference docs from unknown/ to named groups
- Update openapi.json
2026-03-16 06:18:46 -07:00
James Pine 5933cba8e9 add release skills and backfill changelog from GitHub releases
- Backfill CHANGELOG.md from all 17 GitHub releases (was stale at v0.1.0)
- Add draft-release-notes and release-bump agent skills
- Remove stale PATCH_NOTES.md, mlx-test/, move PROJECT_STATUS to docs/notes
- Minor voicebox-server.spec cleanup
2026-03-16 06:15:04 -07:00
James Pine 1b2d492398 add /og preview page and OG image metadata 2026-03-16 05:51:04 -07:00
James Pine faa825290f docs links 2026-03-16 05:33:33 -07:00
James Pine 4a8a9eac14 fix: docker frontend + docs cleanup 2026-03-16 05:28:05 -07:00
Jamie PineandGitHub 3e4d9ff641 Merge pull request #288 from jamiepine/better-docs
Better docs
2026-03-16 05:12:09 -07:00
James Pine 192979a762 docs 2026-03-16 05:11:21 -07:00
James Pine e16cc42d53 enable Edit on GitHub and last updated on all doc pages 2026-03-16 04:45:40 -07:00
James Pine f10e965003 rewrite docs root page, add screenshot 2026-03-16 04:12:11 -07:00
James Pine a8968d4081 rewrite docs introduction based on README content 2026-03-16 04:09:50 -07:00
James Pine 7c4afbe4df expand sidebar groups by default, remove stale plans reference 2026-03-16 04:08:46 -07:00
James Pine a180fcc56f redirect root to /docs 2026-03-16 04:06:38 -07:00
James Pine 1860b8dc92 remove plans/ from docs site 2026-03-16 04:05:14 -07:00
James Pine 1597937535 Merge branch 'main' into better-docs
# Conflicts:
#	backend/main.py
#	docs/content/docs/plans/ADDING_TTS_ENGINES.md
#	docs/content/docs/plans/CUDA_BACKEND_SWAP.md
#	docs/content/docs/plans/CUDA_BACKEND_SWAP_FINAL.md
#	docs/content/docs/plans/EXTERNAL_PROVIDERS.md
#	docs/content/docs/plans/MLX_AUDIO.md
#	docs/content/docs/plans/PROJECT_STATUS.md
2026-03-16 04:01:08 -07:00
Jamie PineandGitHub ac41a89359 Merge pull request #285 from jamiepine/backend-refactor
Backend refactor: modular architecture, style guide, tooling
2026-03-16 03:51:10 -07:00
James Pine 60c0fe3b92 isolate shutdown unload calls so one failure doesn't block the other 2026-03-16 03:50:28 -07:00
James Pine c99828cf76 fix startup db session leak on error (rollback + close in finally) 2026-03-16 03:49:21 -07:00
James Pine 5c4b979480 suppress E402 for app.py (AMD env vars must precede torch import) 2026-03-16 03:47:56 -07:00
James Pine 2d1b0ae820 remove unused _get_cuda_dll_excludes function 2026-03-16 03:46:58 -07:00
James Pine 69486c2a77 handle null duration in story_items migration 2026-03-16 03:44:33 -07:00
James Pine e9f63d6c57 reject model migration to subdirectory of source cache 2026-03-16 03:43:37 -07:00
James Pine 8906bee23e fix docstring for find_voicebox_pid_on_port 2026-03-16 03:43:06 -07:00
James Pine 0dabb121c9 improve startup logging: version, platform, data dir, db stats
Replace verbose startup messages with a clean summary:
- App version, Python version, OS/arch
- Database path (fix None display), data directory
- Profile and generation counts
- Backend, GPU, model cache path
- Clean up stale loading_model status on startup
- Remove noisy progress manager log line
2026-03-16 03:42:39 -07:00
James Pine 944ba227ca soften select focus indicator opacity 2026-03-16 03:22:36 -07:00
James Pine 473bb3e9fb fix take-label race in regeneration, add accessible focus to select
- Use DB COUNT query instead of list length for take-N label to avoid
  TOCTOU race between list_versions and create_version
- Add focus:bg-muted to SelectTrigger for keyboard focus visibility
2026-03-16 03:22:05 -07:00
James Pine 0d0b62ea93 address CodeRabbit review: fix 4 critical + 12 major issues
Critical:
- Remove dead backend.utils.validation PyInstaller hidden import
- Fix story_items table rebuild to preserve track/trim/version columns
- Guard cache migration against same source/destination path
- Fix regeneration audio overwrite (use random uuid suffix per take)

Major:
- Engine selector: validate language on Qwen switch, clear stale modelSize
- Sync language validation regex between profile create and generate (22 langs)
- Guard CUDA download against duplicate concurrent requests
- Only set model_size for engines that support multiple sizes
- Fix 404 swallowed by generic except in history export
- Validate audio_path before FileResponse in export-audio
- Transcription: stream uploads in 1MB chunks, use robust cache check,
  call complete_download() on Whisper download success
- Set clean version as default when effects chain validation fails
- Return explicit error when Windows port occupied by non-voicebox process
2026-03-16 03:12:01 -07:00
James Pine 798cd40f05 delete stale planning docs 2026-03-16 02:59:24 -07:00
James Pine 3187344f01 add model loading status, effects preset dropdown, clean up UI
Backend:
- Generation service reports 'loading_model' status only when model
  is not yet in memory, then 'generating' once inference starts
- Migrate hf_offline_patch.py from print() to logging module
- Update ADDING_TTS_ENGINES.md for post-refactor file paths

Frontend:
- HistoryTable shows 'Loading model...' vs 'Generating...' based on step
- FloatingGenerateBox: replace instruct toggle + inline effects editor
  with an effects preset dropdown (third dropdown after language and engine)
- Instruct UI removed for now (form field preserved for future models)
- Remove focus ring from Select component globally
2026-03-16 02:58:41 -07:00
James Pine 8efcc95606 update Cargo.lock 2026-03-16 02:20:19 -07:00
James Pine 87cab9473d gitignore: stop tracking tauri/src-tauri/gen/Assets.car
Compiled Xcode asset catalog gets regenerated every build. No reason
to track it.
2026-03-16 02:20:02 -07:00
James Pine 7b0fbfb567 rewrite backend README, remove completed refactor plan, update style guide
Replace the outdated backend README (473 lines of stale API docs and
pre-refactor file tree) with a concise architecture document covering
module structure, request flow, backend selection, API domain overview,
and development commands.

Delete REFACTOR_PLAN.md -- all phases are complete.

Update STYLE_GUIDE.md to remove refactor plan references and replace
the verbose target layout with the current actual structure.
2026-03-16 02:18:34 -07:00
James Pine 7c1ea0a1e1 fix: replace netstat with TcpStream + PowerShell for port detection (#277)
On Windows, Voicebox shelled out to netstat.exe on startup to check for
existing server processes. On systems with corrupted DLLs, netstat fails
with 0xc0000142, causing an infinite loading loop.

Replace with:
- TcpStream::connect_timeout() for port-in-use checks (pure Rust)
- PowerShell Get-NetTCPConnection for port-to-PID lookup (built-in cmdlet)
- tasklist for process name verification (unchanged)

Closes #277
2026-03-16 02:15:26 -07:00
James Pine b3012ed10c move CRUD and service modules into services/, platform_detect into utils/
Move 9 business-logic modules from the backend root into services/:
channels, effects, history, profiles, stories, versions, export_import,
transcribe, tts. Move platform_detect.py into utils/.

Backend root now contains only infrastructure (app, main, config, server,
models, build_binary) and docs. All 94 routes verified.
2026-03-16 02:15:20 -07:00
James Pine 88536d27f7 extract routes from main.py into domain routers (Phase 4)
Split the 2,578-line main.py (90 routes) into 12 domain-specific router
modules under routes/. main.py is now a 45-line entry point.

New structure:
- app.py: FastAPI instance, CORS, startup/shutdown, safe_content_disposition
- routes/: health, profiles, channels, generations, history, transcription,
  stories, effects, audio, models, tasks, cuda
- services/cuda.py: moved from cuda_download.py

Also includes Phase 5 database/ package (from parallel agent):
- database/__init__.py re-exports all symbols for backward compat
- database/models.py, session.py, migrations.py, seed.py

All 90 routes verified registered and app imports cleanly.
2026-03-16 02:03:15 -07:00
James Pine 89d6e364d4 move pyproject 2026-03-16 01:48:26 -07:00
James Pine b7781951df comment cleanup 2026-03-16 01:46:19 -07:00
James Pine fe19a9ca47 add style guide, ruff config, generation service extraction, remove Makefile
- Add backend/STYLE_GUIDE.md covering formatting, imports, types, docstrings,
  comments, error handling, async, logging, and naming conventions
- Add pyproject.toml with ruff linter/formatter config (ERA, FIX, isort, pyupgrade)
- Extract generation service (Phase 3): unified run_generation() replaces three
  duplicated closures, serial queue moved to services/task_queue.py
- Delete Makefile in favor of justfile; update all references
- Add Python lint/format/test commands to justfile (check-python, fix-python, test)
- Install ruff, pytest, pytest-asyncio as dev tools in setup-python
- Update REFACTOR_PLAN.md with Phase 3 and Phase 7 completion
2026-03-16 01:35:59 -07:00
Jamie Pine 439fedcbf2 update refactor plan with phase 1+2 progress 2026-03-16 01:10:59 -07:00
Jamie Pine 0813a3d9d6 refactor: remove dead code, deduplicate backends
Phase 1 - delete dead code:
- studio.py, migrate_add_instruct.py, utils/validation.py
- duplicate _profile_to_response in main.py, duplicate asyncio import
- pointless _get_profiles_dir/_get_generations_dir wrappers
- duplicate LANGUAGE_CODE_TO_NAME and WHISPER_HF_REPOS constants

Phase 2 - extract backends/base.py with shared utilities:
- is_model_cached() replaces 7 copy-pasted HF cache checks
- get_torch_device() replaces 5 device detection methods
- combine_voice_prompts() replaces 5 identical implementations
- model_load_progress() ctx manager replaces progress boilerplate in all backends
- patch_chatterbox_f32() replaces identical monkey-patches in both chatterbox backends

net -1078 lines across the backend
2026-03-16 01:10:02 -07:00
Jamie Pine 9514c6596c migrations 2026-03-16 00:54:13 -07:00
Jamie Pine 4e84415da7 refactor start 2026-03-16 00:52:23 -07:00
Jamie Pine 82cd4bf2ef Add dynamic download redirect routes and update README links 2026-03-15 23:22:03 -07:00
Jamie Pine 3c30c5bec1 Update README for v0.2.x: multi-engine, effects, 23 languages, fix download links 2026-03-15 17:12:47 -07:00
Jamie Pine c9d7bc4f27 Fix macOS download links to use .dmg instead of .app.tar.gz 2026-03-15 17:03:17 -07:00
James Pine 34e17bd469 Fix LuxTTS + Chatterbox in prod: bundle espeak/perth data, fix multiprocessing
- collect-all piper_phonemize to bundle espeak-ng-data for LuxTTS phonemization
- Set ESPEAK_DATA_PATH in frozen builds so the C library finds bundled data
- collect-all perth to bundle pretrained watermark model for Chatterbox
- Add multiprocessing.freeze_support() to fix resource_tracker subprocess crash
2026-03-15 16:02:09 -07:00
James Pine aada13a5c9 Collect all inflect files for PyInstaller (fixes typeguard inspect.getsource) 2026-03-15 14:32:10 -07:00
James Pine de8558d197 Fix prod build: download progress, robust stderr, full tracebacks
- Force tqdm disable=False in TrackedTqdm so byte progress works in prod
  (huggingface_hub disables tqdm based on logger level, which prevents
  self.n from updating — our progress tracking needs the counter even
  though we don't render to terminal)
- Harden devnull redirect to test writability, not just None check
- Add full traceback logging to all backend error handlers
- Add chatterbox/luxtts/zipvoice hidden imports and metadata to spec
2026-03-15 14:23:11 -07:00
Jamie Pine 9d79ea367a Only use --noconsole on Windows, macOS/Linux need stdout for Tauri logs 2026-03-15 12:07:35 -07:00
Jamie Pine 04316f7adc Copy metadata for requests/transformers/huggingface-hub to fix PyInstaller metadata lookup 2026-03-15 11:35:05 -07:00
Jamie Pine 4e4361d350 Fix noconsole crash: redirect None stdout/stderr to devnull on Windows 2026-03-15 11:27:35 -07:00
Jamie Pine e9a249587c Collect all linacodec files for PyInstaller (fixes inspect.getsource in Vocos) 2026-03-15 11:06:13 -07:00
Jamie Pine d8a9ed7d15 Enable updater artifacts with v1Compatible for tauri-action sig generation 2026-03-15 10:54:12 -07:00
Jamie Pine 3dbf1c200e Revert "Bump version: 0.2.3 → 0.2.4"
This reverts commit 40fcb8d917.
2026-03-15 10:20:31 -07:00
Jamie Pine 40fcb8d917 Bump version: 0.2.3 → 0.2.4 2026-03-15 10:18:51 -07:00
Jamie Pine ad64d1c3d9 Collect all zipvoice files for PyInstaller (fixes source code error) 2026-03-15 10:18:40 -07:00
Jamie Pine f826e45250 Install chatterbox-tts in CI release workflow 2026-03-15 10:17:23 -07:00
Jamie Pine 3d53c06c5b Bump version: 0.2.2 → 0.2.3 2026-03-15 10:08:56 -07:00
James Pine 9835b9f6d4 fix: prevent stale release data by removing Next.js fetch cache
Replace next: { revalidate: 600 } with cache: 'no-store' on GitHub
API fetches so new releases show up within 5 minutes (in-memory cache
only, no Next.js/Vercel cache layer on top).
2026-03-15 10:07:50 -07:00
Jamie Pine a15dd30b1e Update tauri-action to v0.6 to fix updater JSON and signature generation 2026-03-15 10:05:36 -07:00
Jamie Pine 1d343ac071 Treat missing/draft releases as up-to-date instead of showing error 2026-03-15 09:52:17 -07:00
James Pine ca602de0ae fix: don't reset audio player when unmuting during playback 2026-03-15 09:29:44 -07:00
James Pine cdc0293ca8 feat: add /linux-install page with build-from-source instructions
Linux download card now links to /linux-install instead of a direct
binary download. The page explains the CI situation and gives
clone + setup + build commands.
2026-03-15 09:17:30 -07:00
Jamie Pine e7f749f082 Add luxtts/zipvoice hidden imports to PyInstaller build 2026-03-15 09:13:59 -07:00
Jamie Pine d42e926e5c Bump version: 0.2.1 → 0.2.2 2026-03-15 09:02:10 -07:00
Jamie Pine 32768ea874 Add chatterbox hidden imports to PyInstaller build 2026-03-15 09:00:13 -07:00
James Pine b585e18ccf fix: fade in hero background glow to avoid Safari rendering flash 2026-03-15 08:53:08 -07:00
Jamie Pine 655910457f Auto-update CUDA binary on app update: check version on startup, download if stale 2026-03-15 08:46:17 -07:00
James Pine d6984f1057 fix: remove mix-blend-lighten and drop-shadow causing boxes in Safari 2026-03-15 08:45:40 -07:00
James Pine a637aebe69 feat: show version and total download count on landing page
Fetches download counts across all GitHub releases (paginated) and
displays version, total downloads, and platform list below the CTA.
2026-03-15 08:37:23 -07:00
James Pine a5269d23db Fix keep-server-running on macOS: ignore SIGHUP, watchdog grace period, build script fixes 2026-03-15 08:22:35 -07:00
Jamie Pine fc450e5024 Hide console window for server binary on Windows 2026-03-15 07:57:58 -07:00
Jamie Pine a99c2b572d Show download progress bar for CUDA backend download 2026-03-15 07:50:23 -07:00
Jamie Pine 96289e95f1 Bump version: 0.2.0 → 0.2.1 2026-03-15 06:36:38 -07:00
Jamie PineandGitHub e316b0b4bb Merge pull request #274 from jamiepine/feat/landing-page-redesign
Landing page v0.2.0 redesign
2026-03-15 06:22:04 -07:00
Jamie PineandGitHub 732270b571 Merge pull request #272 from jamiepine/windows-support
Windows support: CUDA detection, cross-platform justfile, clean server shutdown
2026-03-15 06:20:46 -07:00
James Pine 0c6aa15746 Responsive polish: pointer-events-none on animations, sticky header with scroll fade, desktop scroll-to-active fix, iOS audio unlock, player and UI tweaks
- Add pointer-events-none/select-none to feature cards, voice creator, and ControlUI mock
- Sticky header with gradient fade overlay (matching real app 3-layer technique)
- Fix desktop scroll-to-active: separate mobile/desktop card refs to prevent mobile refs overwriting desktop
- Scroll selected card to 2nd row when outside safe zone above generate box
- iOS Safari audio unlock via WaveSurfer's actual media element
- Player: accent fill play/pause button, padding on volume slider, remove close button
- Profile cards: fixed 143px height, mobile edge fades with scroll-aware left fade
- Generate box: accent effect pill when active, white fill sparkle icon, edge-aligned on desktop
- Voice creator: animated waveform background with height-based bars
- 12 profiles (added Attenborough, Zendaya, Obama) for 4-row grid with scroll
2026-03-15 06:17:54 -07:00
Jamie Pine 410413dc57 Watchdog respects keep-server-running setting via /watchdog/disable endpoint 2026-03-15 06:05:17 -07:00
Jamie Pine e239be5bbb Review fixes: CUDA restore in finally, os._exit on Windows, taskkill /T for process tree, build-server-cuda error handling, db-init path 2026-03-15 05:43:26 -07:00
James Pine f80782a90a Landing page v0.2.0 updates: multi-engine copy, star count, model cards, voice creator section, responsive ControlUI, iOS audio fix
- Replace Qwen-specific copy with multi-engine messaging across hero, meta, and features
- Add GitHub star count fetched server-side via /api/stars with Spacedrive-style navbar badge
- Replace 'Why Voicebox exists' section with model cards for all 4 TTS engines
- Enable Linux download card (was 'Coming soon')
- Update GPU support copy to include ROCm, Intel Arc, DirectML
- Add Voice Creator section with animated 3-tab UI (upload, mic, system audio) and waveform background
- Make ControlUI responsive: horizontal scroll cards on mobile, stacked layout, scroll-to-active profile
- Fix iOS Safari audio autoplay (unlock AudioContext on user gesture)
- Fix hero logo square background with mix-blend-lighten
- Remove generation length green coloring, use gray with accent highlights
- Comment out grain overlay (visible tile seams)
- Remove player close button, stack waveform above controls on mobile
- Fixed-height profile cards (143px) with space between badges and buttons
2026-03-15 04:53:28 -07:00
Jamie Pine f1ba73a386 Address review: validate parent-pid, ensure binaries dir exists, fix Xcode typo 2026-03-15 04:09:49 -07:00
Jamie Pine f1963740b4 Fix server binary build, watchdog logging, pedalboard import, window close loop 2026-03-15 04:04:56 -07:00
Jamie Pine 4d6c976ad9 Windows support: CUDA detection, justfile cross-platform, clean server shutdown 2026-03-15 00:02:13 -07:00
Jamie Pine 8377152d86 Redesign landing page with animated ControlUI hero
New Spacedrive-inspired landing page with dark warm color system, glassmorphic navbar, feature cards with animated illustrations, and an interactive ControlUI mockup that cycles through voice generations with real audio playback via WaveSurfer.

The ControlUI demo script is fully data-driven - profiles, generation text, audio samples, and effects are all configurable from a single DEMO_SCRIPT array.

Includes 6 real voice samples (Jarvis, Morgan Freeman, Sam Altman, Samuel L. Jackson, Linus Tech Tips, Fireship) converted to webm opus.
2026-03-14 23:08:29 -07:00
Jamie PineandGitHub 7a511e3756 Merge pull request #271 from jamiepine/feat/post-processing-effects
Add post-processing audio effects system
2026-03-14 12:14:39 -07:00
Jamie PineandGitHub 6d261c44a1 Merge branch 'main' into feat/post-processing-effects 2026-03-14 12:14:26 -07:00
Jamie Pine 103e98b38f github runners suck 2026-03-14 12:13:45 -07:00
Jamie Pine 1c61b47a64 Glassmorphic active state for sidebar buttons with accent border shine 2026-03-14 12:11:07 -07:00
Jamie Pine 626e3740e1 Auto-select first story when navigating to Stories tab 2026-03-14 11:14:46 -07:00
Jamie Pine 310a4acb02 Add source version selection when applying effects, voices tab overhaul with inline inspector 2026-03-14 11:07:32 -07:00
Jamie Pine 899b90202b Add version control to track editor, restyle story list
- Story items can be pinned to a specific generation version via
  toolbar dropdown (shows when clip is selected and has >1 version)
- version_id column on story_items with migration, validated against
  the generation's versions before saving
- Split/duplicate preserve the source clip's pinned version
- Export and playback resolve version-specific audio paths
- Extracted _build_item_detail helper in stories.py (DRY cleanup)
- Story list restyled from rounded cards to flat rows with rounded
  hover/active states, gradient header fade, and dynamic bottom
  padding that accounts for track editor + generate box
2026-03-14 09:56:27 -07:00
Jamie Pine e8d54d52d3 Add favorites, effects badge on profiles, UI polish
- Add is_favorited column with toggle endpoint and star button on history
- Show sparkles icon on profile cards that have effects configured
- Gold ring on selected profile cards
- Smaller, gray action buttons with brighter hover
- Clamp player time to duration to prevent runaway playback
- Align profile card icon to top for wrapped names
- Flush bottom corners on history card when versions expanded
- Simplify .gitignore data/ rule
2026-03-14 09:10:56 -07:00
Jamie Pine 00c5b75ffb Regenerate as new version, UI polish, and bugfixes
- Add /generate/{id}/regenerate endpoint that creates a new take version
- Wire regenerate into history dropdown with SSE progress + autoplay
- Add normalize_audio to regenerate path
- Remove duplicate Regenerate menu item
- Show disabled ellipsis menu during generation instead of hiding it
- Fix sf.write format kwarg broken by asyncio.to_thread migration
- Rename clean version label to 'original', effects to 'version-N'
- Show effects chain names in version list instead of 'N fx'
- Include all versions in export package
- Clean up version panel padding
2026-03-14 08:34:58 -07:00
Jamie Pine 25134b4ba9 Fix player not loading new version after applying effects
Reload the player with the version-specific audio URL when effects are
applied to the currently playing generation. Also consolidate the
instruct/effects buttons into a single button with the effects editor
shown inline when instruct mode is open.
2026-03-14 08:01:45 -07:00
Jamie Pine 3d922ec846 Fix review findings: toggle logic, preset saving, version lookup, async audio ops
- Fix inverted effects toggle in FloatingGenerateBox
- Add Save button + API method for editing custom effect presets
- Return early on effects save failure in ProfileForm
- Fix no-op ternary in effectsStore
- Handle duplicate preset names with proper 400 response
- Use effects_chain is None instead of label for clean version lookup
- Move blocking audio ops to asyncio.to_thread in async endpoints
- Log warnings instead of silently swallowing parse errors
2026-03-14 07:47:06 -07:00
James Pine 638820c839 Add post-processing audio effects system
Adds a full effects pipeline powered by Spotify's pedalboard library,
enabling users to apply professional DSP effects (flanger, reverb, delay,
compressor, pitch shift, filters, gain) to generated audio.

Key features:
- Effects chain editor with drag-and-drop reordering (dnd-kit)
- Generation versions: clean copy always saved, processed versions created on top
- Built-in presets (Robotic, Radio, Echo Chamber, Deep Voice) + custom user presets
- Per-profile default effects chain (auto-applied to new generations)
- Per-generation effects override from the generation form
- Apply effects to existing generations from history (creates new version)
- Ephemeral preview endpoint for auditioning effects without persisting
- Dedicated Effects sidebar tab with preset management and live preview
- Version switcher in history cards with expandable panel
- Backward-compatible: existing generations backfilled as clean versions
2026-03-14 07:11:56 -07:00
Jamie Pine 7cbf5a1ded Use Namespace runner for Linux release build 2026-03-14 05:38:25 -07:00
Jamie Pine e89a7eb7e7 Windows dev experience: CUDA detection, GPU display cleanup, hide drag region, dev-mode update status 2026-03-14 03:24:39 -07:00
Jamie Pine e18757bab3 Skip AppImage on Linux, build deb/rpm only 2026-03-14 03:04:59 -07:00
Jamie Pine 0e6c678fc3 Add Windows support to justfile 2026-03-14 02:41:59 -07:00
Jamie Pine 942dabbcac Install CPU-only PyTorch before requirements.txt on Linux
The previous ordering let requirements.txt pull CUDA-enabled torch
with all nvidia deps first, then the CPU override only swapped the
torch wheel while leaving ~3GB of nvidia packages installed.
2026-03-14 00:55:43 -07:00
Jamie Pine b915825165 Add libasound2-dev to Linux release deps 2026-03-13 21:36:46 -07:00
Jamie Pine f3fc63942f Fix Linux release build exceeding 4GB PyInstaller limit
Install CPU-only PyTorch on Linux and exclude nvidia modules from
non-CUDA PyInstaller builds.
2026-03-13 21:19:24 -07:00
Jamie Pine 9044b986f3 Move tauri imports behind platform abstraction, merge CUDA build into release workflow
- Add openPath and pickDirectory to PlatformFilesystem interface
- Remove direct @tauri-apps/plugin-shell and plugin-dialog imports from app
- Merge build-cuda.yml into release.yml as a parallel job
2026-03-13 11:33:32 -07:00
Jamie Pine b01076b6b3 Bump version: 0.1.13 → 0.2.0 2026-03-13 11:06:40 -07:00
Jamie PineandGitHub 5121c76e39 Merge pull request #269 from jamiepine/feat/async-generation-queue
feat: async generation queue
2026-03-13 10:58:18 -07:00
Jamie Pine 49ebf6222e fix SSE cleanup, filter add popover to completed only, derive isGenerating from pending set, handle not_found status 2026-03-13 10:57:28 -07:00
Jamie Pine 509b0e71cc responsive layout fixes, version in sidebar, fixed voice card height, hide player title at small widths 2026-03-13 10:44:53 -07:00
Jamie Pine 81f8be1a94 defer story add until TTS completes, add generating pill to story editor, fix item placement per-track 2026-03-13 10:28:20 -07:00
Jamie Pine 655a60ca81 feat: async generation queue with serial execution
Generations now return immediately with a 'generating' status and appear
in history right away. TTS runs in a serial background queue to avoid
GPU contention. Users can kick off multiple generations without blocking.

- Async POST /generate creates DB record immediately, queues TTS work
- Serial generation queue prevents concurrent GPU access (Metal/CUDA/CPU)
- SSE endpoint GET /generate/{id}/status for real-time completion tracking
- Retry endpoint POST /generate/{id}/retry for failed generations
- Store engine and model_size on generation records for retry support
- History cards show animated loader (react-loaders) for generating/playing
- Failed generations show retry button instead of actions menu
- Model downloads happen inline in the queue instead of rejecting with 202
- Stale 'generating' records marked as failed on server startup
- Autoplay on generate setting (default: on)
- Show engine name on generation cards
- Remove sidebar generation spinner
- Checkbox alignment fix in settings
2026-03-13 10:02:41 -07:00
Jamie PineandGitHub 52285362ce Merge pull request #268 from jamiepine/feat/model-management-improvements
feat: model management improvements and folder migration
2026-03-13 09:16:43 -07:00
Jamie Pine 3ea587797f feat: model management improvements and folder migration
- Add model folder migration with byte-level progress tracking (backend + UI)
- Custom models directory support via VOICEBOX_MODELS_DIR env var passed to sidecar
- Hardcoded model descriptions displayed in model detail cards
- Open model folder button in storage location row
- Remove 'not downloaded' badge from model cards
- Fix server settings scroll offset for audio player
- Fix shell open permission to allow file paths
- Add normalize toggle to generation settings
2026-03-13 08:38:20 -07:00
Jamie PineandGitHub 325714bb83 Merge pull request #266 from jamiepine/feat/chunked-tts
feat: chunked TTS generation for long text (engine-agnostic)
2026-03-13 08:23:53 -07:00
James Pine 9aa7080c51 refactor: restructure server settings and models UI
- Split chunking/crossfade sliders into dedicated GenerationSettings card
- Merge connection status badges into ConnectionForm (remove ServerStatus card)
- 2-column grid layout for the entire settings page
- GPU Acceleration: remove icon, badge, and MLX info card
- Models: merge 'Other Voice Models' into single 'Voice Generation' list
- Model detail: remove 'Downloaded' badge, border above actions, swap
  badges above stats row, match disk size font to stats
2026-03-13 07:26:46 -07:00
James Pine 97292ecef7 feat: add chunk crossfade slider (0ms = hard cut)
Persisted setting (default 50ms) controls how audio chunks are blended
together.  Set to 0 for a clean hard cut with no overlap.
2026-03-13 06:48:06 -07:00
James Pine 837f8525d8 feat: add auto-chunking limit slider to settings
Persisted setting (default 800 chars) controls how long text is split
before generation.  Lower values improve quality for long outputs by
keeping each chunk well within the model's context window.

- Slider in Server Connection settings (100–2000 chars, step 50)
- Stored in localStorage via Zustand persist
- Passed as max_chunk_chars on every generation request
- Frontend text limit raised to 50,000 to match backend
2026-03-13 06:35:39 -07:00
James Pine 70ca7f66cb feat: chunked TTS generation for long text (engine-agnostic)
Text exceeding max_chunk_chars (default 800) is automatically split at
sentence boundaries, generated per-chunk, and concatenated with a 50ms
crossfade.  Works with all engines (Qwen, LuxTTS, Chatterbox, Turbo).

- Abbreviation-aware sentence splitter (Dr., Mr., e.g., decimals)
- CJK sentence-ending punctuation support
- Paralinguistic tag preservation ([laugh], [cough], etc.)
- Per-chunk seed variation to avoid correlated RNG artefacts
- Per-chunk Chatterbox trim (catches hallucination at each boundary)
- max_chunk_chars exposed as per-request param on GenerationRequest
- Text max_length raised to 50,000 characters

Closes #99
2026-03-13 06:21:34 -07:00
Jamie PineandGitHub c12b5d6f0a Merge pull request #265 from jamiepine/feat/paralinguistic-tags
feat: paralinguistic tag autocomplete for Chatterbox Turbo
2026-03-13 05:55:06 -07:00
James Pine 139fa38e3f fix: address review feedback for ParalinguisticInput
- Initialize lastSerializedRef to empty string so first-mount hydration
  always runs (fixes initial value not rendering)
- Guard arrow-key menu nav against empty filteredTags (avoids NaN index)
- Disable ARIA role/multiline and detach event handlers when disabled
- Add onBlur to close autocomplete dropdown when editor loses focus
- Chain exception with 'from e' in unload endpoint for better tracebacks
2026-03-13 05:52:06 -07:00
Jamie PineandGitHub 0e9f5db40f Merge pull request #264 from jamiepine/fix/chatterbox-float64-dtype
fix: Chatterbox float64 dtype mismatch + model unload button
2026-03-13 05:40:46 -07:00
James Pine 2f535a772f fix: load model into local var before patching to avoid half-initialised state
Apply local-var-then-assign pattern to chatterbox_backend.py (multilingual)
to match the turbo backend. Also use _current_model_size fallback in
unload, delete, and status endpoints for consistent Qwen model size checks.
2026-03-13 05:40:18 -07:00
James Pine b420637957 feat: paralinguistic tag autocomplete for Chatterbox Turbo
Type / in the text input when using Chatterbox Turbo to open an
autocomplete dropdown with 9 supported paralinguistic tags ([laugh],
[chuckle], [gasp], [cough], [sigh], [groan], [sniff], [shush],
[clear throat]).

- contentEditable div replaces textarea for Turbo engine only
- Tags render as inline styled badges
- Pasting text with [tag] patterns auto-converts to badges
- Badges serialize back to plain [tag] text for the API
- Dropdown portalled to body, opens above caret to avoid overflow
2026-03-13 05:19:23 -07:00
James Pine bfd7b815a5 fix: patch S3Tokenizer.log_mel_spectrogram for float64→float32 cast
The actual dtype mismatch was in S3Tokenizer.log_mel_spectrogram, not
VoiceEncoder.forward. librosa.load returns float64 numpy, which
torch.from_numpy preserves as double. The STFT output (double) then
hits _mel_filters (float32) in a matmul at s3tokenizer.py:163.

Now patching both entry points after model load:
1. S3Tokenizer.log_mel_spectrogram — cast audio to float32 before STFT
2. VoiceEncoder.forward — cast mels to float32 before LSTM

Remove debug traceback logging (no longer needed).
2026-03-13 05:04:29 -07:00
James Pine cac80f6af0 feat: add per-model unload endpoint and UI button
- POST /models/{model_name}/unload — unloads a specific model from
  memory without deleting from disk, supports all engine types
- Frontend: Unload button in model detail dialog when model is loaded
- Delete button remains disabled while loaded (unload first)
2026-03-13 04:50:56 -07:00
James Pine 47ce4cafdf fix: patch VoiceEncoder.forward to cast float64 mels to float32
The previous approach of patching librosa.load didn't work because
melspectrogram itself performs float64 math (numpy dot, signal.lfilter)
regardless of input dtype. The actual mismatch happens when pack()
creates a float64 tensor from the mel arrays and passes it into the
float32 LSTM weights in VoiceEncoder.forward().

Fix by monkey-patching VoiceEncoder.forward() to call mels.float()
before the LSTM, ensuring the input always matches the model dtype.
2026-03-13 04:41:43 -07:00
James Pine bfe912e41a fix: specify WAV format for atomic save temp file
soundfile cannot infer format from .tmp extension, causing all
generations to fail with 'No format specified and unable to get
format from file extension'
2026-03-13 04:34:26 -07:00
James Pine 5ccf79a8f7 Revert "fix: cast librosa float64 audio to float32 for Chatterbox voice encoder"
This reverts commit 1d32170c2e.
2026-03-13 04:28:00 -07:00
James Pine 1d32170c2e fix: cast librosa float64 audio to float32 for Chatterbox voice encoder
The upstream VoiceEncoder's melspectrogram only casts to float32 when
hp.normalized_mels is True (it defaults to False), so librosa's float64
output flows through as double tensors into float32 model weights,
causing 'expected m1 and m2 to have the same dtype, but got: float !=
double'. Fix by monkey-patching prepare_conditionals in both Chatterbox
and Chatterbox Turbo backends to ensure librosa.load returns float32.
2026-03-13 04:15:20 -07:00
James Pine ca74c155e2 fix: pass language parameter to Qwen TTS models and sync form with profile language
Both PyTorch and MLX backends silently dropped the language parameter —
it was accepted by generate() but never forwarded to the underlying
Qwen3-TTS model, causing it to default to auto-detection which
frequently confuses similar languages (e.g. Portuguese for Spanish).

- Add LANGUAGE_CODE_TO_NAME mapping (ISO 639-1 to full name) to both backends
- PyTorch: pass language= to generate_voice_clone()
- MLX: pass lang_code= to all 4 model.generate() call sites
- Frontend: auto-sync generation form language with selected voice profile

Closes #97
2026-03-13 04:04:04 -07:00
James Pine 1f770a157d fix: mismatched JSX closing tag in ModelManagement 2026-03-13 03:59:30 -07:00
Jamie PineandGitHub d64e24d422 Merge pull request #230 from haosenwang1018/docs/readme-grammar-profile-management
docs: fix minor README grammar in feature bullets
2026-03-13 03:56:55 -07:00
Jamie PineandGitHub 77d86ba835 Merge pull request #88 from Balneario-de-Cofrentes/fix/restrict-cors-origins
security: restrict CORS to known local origins
2026-03-13 03:56:15 -07:00
Jamie PineandGitHub 986a748420 Merge pull request #161 from ageofalgo/feat/docker-web-deployment
feat: add Docker + web deployment support
2026-03-13 03:55:04 -07:00
James Pine 50e01d17f8 fix: remove unused TTS_MODE env var from docker-compose
TTS_MODE is not read by any code in the backend — it only exists in
unimplemented planning docs. Remove it to avoid confusing users.
2026-03-13 03:53:15 -07:00
Jamie PineandGitHub 084c51b983 Merge pull request #215 from mikeswann/main
Update prerequisites in markdown with Tauri deps
2026-03-13 03:52:34 -07:00
Jamie PineandGitHub efbbbc7ec1 Merge branch 'main' into main 2026-03-13 03:52:22 -07:00
Jamie PineandGitHub 8e7f0cb9ad Merge pull request #133 from rayl15/feat/network-access-toggle
feat: add network access toggle to server settings
2026-03-13 03:47:35 -07:00
Jamie PineandGitHub 3357a06cba Merge pull request #263 from jamiepine/fix/atomic-save-error-handling
fix: atomic audio save with error handling and filesystem health endpoint
2026-03-13 03:45:26 -07:00
Jamie PineandGitHub f58c7c1cf3 Merge pull request #262 from jamiepine/feat/linux-rocm-whisper-turbo
feat: Linux support, AMD ROCm, Whisper Turbo, and spawn fix
2026-03-13 03:44:36 -07:00
James Pine ea41213123 fix: atomic audio save with errno-specific error handling and filesystem health endpoint
- save_audio() now writes to .tmp then os.replace() for atomic writes
- /generate endpoint catches OSError with specific messages for ENOENT, EACCES, ENOSPC, and BrokenPipeError
- New /health/filesystem endpoint checks directory existence, write permissions, and disk space
- New DirectoryCheck and FilesystemHealthResponse models

Cherry-picked and expanded from #178 (@Vaibhavee89)
2026-03-13 03:43:42 -07:00
James Pine b5801891b8 feat: Linux support, AMD ROCm, Whisper Turbo, and spawn fix
Cherry-picked and adapted from PR #89 and #214:

- Linux audio capture via PulseAudio/PipeWire monitor sources (cpal)
- AMD ROCm GPU support: HSA_OVERRIDE_GFX_VERSION env var, ROCm detection
- Whisper Turbo model (openai/whisper-large-v3-turbo) in all endpoints
- Cleaner Whisper language handling via generate_kwargs
- tauri::async_runtime::spawn fix to prevent panic on app shutdown
- Enable Linux (ubuntu-22.04) in release CI matrix
2026-03-13 03:35:18 -07:00
Jamie PineandGitHub 8f77c041f5 Merge pull request #152 from mpecanha/fix-offline-mode-crash
Fix: Prevent crashes when HuggingFace is unreachable
2026-03-13 03:31:23 -07:00
James Pine 5a3f3ba030 Merge remote-tracking branch 'origin/main' into feat/docker-web-deployment 2026-03-13 03:21:39 -07:00
Jamie PineandGitHub 3c25ee6e2c Merge pull request #243 from ways2read/a11y/screen-reader-and-keyboard-improvements
a11y: screen reader and keyboard improvements
2026-03-13 03:18:42 -07:00
James Pine b92b0dd508 merge: resolve conflicts with latest main 2026-03-13 03:16:56 -07:00
Jamie PineandGitHub 670900bf5a Merge pull request #258 from jamiepine/feat/chatterbox-turbo
feat: Chatterbox Turbo engine + per-engine language lists
2026-03-13 03:14:44 -07:00
James Pine 219cfb1605 docs: update PROJECT_STATUS.md to reflect multi-engine architecture
- Reflects merged PRs: #254 (LuxTTS/multi-engine), #257 (Chatterbox), #252 (CUDA swap), #238 (download UI)
- Updated architecture diagram to show all 4 TTS engines
- Added TTS engine comparison table and multi-engine architecture section
- Marked resolved bottlenecks (singleton backend, frontend Qwen assumptions)
- Updated PR triage: marked #194 and #33 as superseded
- Added 'Adding a New Engine' guide (now ~1 day effort)
- Updated recommended priorities to reflect current state
- Added new API endpoints (CUDA, cancel, active tasks)
2026-03-13 02:39:10 -07:00
James Pine bf728a780c feat: add Chatterbox Turbo engine and per-engine language lists
- New ChatterboxTurboTTSBackend wrapping ChatterboxTurboTTS (ResembleAI/chatterbox-turbo)
- English-only 350M model with paralinguistic tag support ([laugh], [cough], [chuckle])
- Bypasses upstream token=True bug by calling snapshot_download(token=None) + from_local()
- Same CPU-on-macOS forcing and torch.load monkey-patching as multilingual backend
- Full engine integration: generate, stream, model status/download/delete endpoints
- Language dropdown now shows only languages supported by the selected engine
- Per-engine language maps: Qwen (10), LuxTTS (en), Chatterbox (23), Turbo (en)
- Auto-switches to English when selecting English-only engines
- Backend language regex expanded to accept all 23 Chatterbox languages
2026-03-13 02:35:10 -07:00
Jamie PineandGitHub 3e6513c0fb Merge pull request #257 from jamiepine/feat/chatterbox
feat: Chatterbox TTS engine with multilingual voice cloning
2026-03-13 02:12:56 -07:00
James Pine c54ee14173 fix: model loaded icon uses accent-colored CircleCheck, show size for loaded models, fix generate box overlapping player on stories route 2026-03-13 02:09:32 -07:00
James Pine cc07d4d3c9 fix: download progress tracking for all engines and inline progress UI
- Add HFProgressTracker to LuxTTS and Chatterbox backends so tqdm-based
  file-level download progress reaches the frontend (previously only Qwen
  had this, LuxTTS/Chatterbox showed a static spinner)
- Add progress/current/total/filename fields to ActiveDownloadTask so the
  /tasks/active polling endpoint carries progress data
- Show inline progress bar + bytes in the model list and detail modal,
  poll at 1s during active downloads (5s otherwise)
- Fix GpuAcceleration crash: cudaStatusLoading was referenced before
  initialization in its own useQuery declaration
2026-03-13 02:09:32 -07:00
James Pine 9beb9d7fec fix: install chatterbox-tts with --no-deps to avoid numpy pin conflict
chatterbox-tts 0.1.6 pins numpy<1.26 and torch==2.6 which are
incompatible with Python 3.12+. Install with --no-deps and list
its sub-dependencies explicitly in requirements.txt.

Also removes HFProgressTracker from chatterbox backend to avoid
'generator didn't stop after throw()' errors from tqdm patching.
2026-03-13 02:09:32 -07:00
James Pine 76bb207b2b feat: add Chatterbox TTS engine for multilingual voice cloning
- New ChatterboxTTSBackend wrapping ChatterboxMultilingualTTS (ResembleAI/chatterbox)
- Supports 23 languages including Hebrew, forces CPU on macOS (MPS issue)
- Monkey-patches torch.load for CPU loading, forces eager attention for compatibility
- trim_tts_output utility cuts trailing silence/hallucination from Chatterbox output
- Full engine integration: /generate, /generate/stream, model status/download/delete
- Hebrew (he) added to supported languages in frontend and backend validation
- Single flat model dropdown extended with Chatterbox option in both generation UIs
- ModelManagement UI groups LuxTTS and Chatterbox under 'Other Voice Models' section
2026-03-13 02:09:32 -07:00
Jamie PineandGitHub 3576521d62 Merge pull request #254 from jamiepine/feat/luxtts
feat: LuxTTS integration — multi-engine TTS support
2026-03-13 02:04:46 -07:00
Jamie PineandGitHub 2df4ece388 Merge pull request #210 from ieguiguren/fix/linux-nvidia-gbm-buffer
fix: Linux NVIDIA GBM buffer crash + WebKitGTK microphone access
2026-03-13 01:55:58 -07:00
Jamie PineandGitHub cbb4979ed6 Merge pull request #175 from Vaibhavee89/fix/profile-duplicate-name-validation
Fix #134: Add validation for duplicate profile names
2026-03-13 01:55:30 -07:00
James Pine 753158c1c9 fix: address review feedback — race condition, GPU safety, task GC
- Add threading lock to get_tts_backend_for_engine() to prevent race
  condition where concurrent requests could create duplicate backend
  instances (double-checked locking pattern)
- Fix LuxTTS generate: call .detach().cpu() before .numpy() so it
  works on GPU/MPS devices, not just CPU
- Store background download tasks in a module-level set to prevent
  garbage collection before completion (asyncio.create_task fire-and-
  forget pattern)
- Deduplicate cache_key computation in LuxTTS create_voice_prompt
- Prefix unused sr variable with underscore
2026-03-13 01:54:09 -07:00
Jamie PineandGitHub 573f82a7e6 Merge pull request #250 from pandego/fix/docs-align-local-port-17493
docs: align local API port examples with current dev flow
2026-03-13 01:53:28 -07:00
James Pine 1e5afc2bef fix: LuxTTS generation and preserve model selection after generate
- Fix silent Zod validation failure when LuxTTS selected (modelSize was
  set to 'default' which failed enum validation, preventing form submit)
- Preserve engine, model size, and language after successful generation
  instead of resetting to defaults
2026-03-13 00:21:43 -07:00
James Pine 163528bf69 fix: single flat model dropdown, linacodec dep, quiet sidecar script
- Combine engine + model size into one flat dropdown (Qwen3-TTS 1.7B,
  Qwen3-TTS 0.6B, LuxTTS) in both FloatingGenerateBox and GenerationForm
- Add linacodec git dep to requirements.txt (uv-only source, pip can't
  resolve it from Zipvoice's pyproject.toml)
- Remove redundant transitive deps from requirements.txt
- Quiet the sidecar setup script (was printing misleading instructions)
2026-03-13 00:21:43 -07:00
James Pine e1ad7a6e73 fix: add piper-phonemize find-links for LuxTTS install
piper-phonemize has no PyPI wheels — needs custom find-links URL
from k2-fsa.github.io. Removed redundant transitive deps that
Zipvoice already declares.
2026-03-13 00:21:43 -07:00
James Pine 411e91bb19 docs: add just commands to README dev quick start 2026-03-13 00:21:43 -07:00
James Pine 05cf163744 chore: add justfile for streamlined dev setup and workflow
Adds 'just' as the recommended dev tool: 'just setup' for one-time
install, 'just dev' to run backend + frontend in one terminal.
Updates CONTRIBUTING.md to document just as the primary setup method.
2026-03-13 00:21:43 -07:00
James Pine d46eb5bcc6 feat: add LuxTTS as second TTS engine with multi-engine support
Introduce LuxTTS (ZipVoice) alongside Qwen TTS, enabling users to choose
between engines at generation time. LuxTTS offers fast, English-focused
voice cloning at 48kHz with ~1GB VRAM.

Backend:
- Add LuxTTSBackend with encode_prompt/generate_speech integration
- Multi-engine registry (get_tts_backend_for_engine) replacing singleton
- Engine-prefixed voice prompt cache keys to avoid collisions
- Engine field on GenerationRequest (default 'qwen' for backward compat)
- Engine dispatch in /generate and /generate/stream endpoints
- LuxTTS in model status, download, and delete maps

Frontend:
- TTS Engine selector dropdown in GenerationForm (Qwen TTS / LuxTTS)
- Conditionally hide Model Size and Delivery Instructions for LuxTTS
- Engine field added to TypeScript types and Zod schema
- LuxTTS section in Model Management page
2026-03-13 00:21:43 -07:00
Jamie PineandGitHub 6359dee406 Merge pull request #252 from jamiepine/feat/cuda-backend-swap
feat: CUDA backend swap via binary download and restart
2026-03-13 00:20:40 -07:00
James Pine a69c216794 fix: address review feedback on CUDA backend swap
- Use YAML block scalar for inline run with colons (build-cuda.yml)
- Explicitly set VOICEBOX_BACKEND_VARIANT=cpu instead of setdefault (server.py)
- Use Path.replace() for atomic move on all platforms (cuda_download.py)
- Log actual exception in checksum fetch warning (cuda_download.py)
2026-03-13 00:20:05 -07:00
James Pine 2867421550 feat: CUDA backend swap via binary download and restart
Add the ability to download a CUDA-enabled backend binary (~2.4 GB) and
swap it in via a backend-only restart, solving the #1 user pain point
(19 open 'GPU not detected' issues caused by GitHub's 2 GB asset limit).

Backend:
- cuda_download.py: download from R2 (primary) or GitHub split-parts
  (fallback), SHA-256 verification, atomic writes, progress via SSE
- 4 new endpoints: GET/POST/DELETE /backend/cuda-*, GET cuda-progress
- server.py: --version flag, auto-detect variant from binary name
- build_binary.py: --cuda flag for CUDA PyInstaller builds
- split_binary.py: split large binaries into <2GB GitHub Release assets
- CI workflow for building CUDA binary

Tauri:
- restart_server command (stop -> wait -> start)
- start_server prefers CUDA binary from {data_dir}/backends/ if present
- Version mismatch check: runs --version before launching CUDA binary

Frontend:
- GpuAcceleration component: download, progress, restart, switch, delete
- API client + types for CUDA status and management
- Platform lifecycle: restartServer() on Tauri/Web
- Aggressive 1s health polling during restart for fast reconnection
2026-03-13 00:04:12 -07:00
Jamie PineandGitHub 758577fd4b Merge pull request #238 from luminest-llc/feat/download-cancel-and-error-ui
Added download cancel/clear UI, fixed model downloading
2026-03-13 00:03:37 -07:00
pandego 3d2506767d docs: address review nits for API generator 2026-03-13 05:08:25 +01:00
pandego cdef2163c1 docs: align local API port examples with current dev flow 2026-03-12 12:17:50 +01:00
Richard Orme 9955e1dcb7 a11y: address PR feedback and polish docs
- HistoryTable: skip row key handler when focus is on Actions button (Enter/Space)
- StoryList: expose selected story (aria-pressed, 'Selected' in label)
- ProfileCard: skip card key handler when focus is on Export/Edit/Delete
- VoicesTab: keep table semantics; edit button in first cell instead of role=button on row
- PR-ACCESSIBILITY.md: 'Fine-tune' wording, 'focus on the text area' phrasing

Made-with: Cursor
2026-03-07 12:36:02 -08:00
Richard Orme 19a28bf6c5 a11y: screen reader and keyboard improvements
- Audio player: aria-labels for Play/Pause, Loop, Mute, Close; labelled playback and volume sliders
- Generation: aria-labels for Generate speech and Fine tune instructions buttons
- Voice cards: focusable, labelled, Enter/Space to select
- History rows: focusable, labelled, Enter/Space to play; transcript textarea labelled
- Voices tab: focusable rows, labelled, Enter/Space to edit; Actions button labelled
- Model management: focusable model rows and labelled Download/Delete buttons
- Server tab: regions with aria-label and tabIndex for Connection, Status, App Updates
- Stories: focusable story rows, labelled, Enter/Space to select; Actions and track editor buttons labelled
- Voice profile samples: Play/Pause/Stop and mini-player slider labelled

Tested with NVDA and Narrator on Windows. See docs/PR-ACCESSIBILITY.md for full description.

Made-with: Cursor
2026-03-07 12:02:33 -08:00
Daddy Raegen a8ecf3f31d refactor: encapsulate task clearing behind TaskManager.clear_all() 2026-03-06 20:33:21 -05:00
Daddy Raegen d744e634a8 fix: address PR review feedback for download cancel/error UI
- Fix transcribe_audio to use whisper-large-v3 mapping (not openai/whisper-large)
- Propagate error field in progress-only fallback path for get_active_tasks
- Use removed return value in cancel endpoint to vary response message
- Add error rollback to handleCancel with toast on failure
- Make isCancelling per-model instead of global
- Fix inverted chevron icons in Problems panel
- Move all clears under lock in clear_all_tasks
- Simplify cancel_download to use dict.pop()
2026-03-06 10:52:57 -05:00
Daddy Raegen a362d7de2a feat: add download cancel/clear UI, fix whisper-large and error reporting
- Add cancel (X) button on downloading and errored model items
- Add collapsible Problems panel (VS Code-style) showing error details
- Add "Clear All" button to reset all stale download/error state
- Add POST /models/download/cancel endpoint to dismiss individual downloads
- Add POST /tasks/clear endpoint to reset all task and progress state
- Include error messages in /tasks/active response for visibility
- Capture SSE error messages client-side for immediate display
- Fix whisper-large using wrong HF repo (openai/whisper-large → openai/whisper-large-v3)
- Fix Whisper HF repo mapping in both PyTorch and MLX backends
- Shorten error toast to point users to Problems panel instead of wall of text
2026-03-06 00:56:14 -05:00
OpenClaw Bot 3f10a70d4c docs: fix minor grammar in feature bullets 2026-03-04 04:39:28 +00:00
mikeswannGitHubcoderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
d0dfe78701 Update CONTRIBUTING.md
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2026-02-28 10:36:34 +01:00
mikeswannandGitHub 172addd918 Update README.md 2026-02-28 00:29:23 +01:00
mikeswannandGitHub ada309cfb9 Update CONTRIBUTING.md 2026-02-28 00:28:01 +01:00
IvanandClaude Opus 4.6 30ee07c2e3 fix: scope DMABUF workaround to Linux+NVIDIA, add origin validation
Address CodeRabbit review feedback:
- Makefile: only set WEBKIT_DISABLE_DMABUF_RENDERER=1 when running on
  Linux with an NVIDIA GPU detected via lspci
- main.rs: validate webview origin before auto-granting microphone
  permission — only allow for trusted local origins (tauri://, localhost,
  127.0.0.1)

Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-02-27 07:01:32 +01:00
IvanandClaude Opus 4.6 d21c63b52c fix: enable microphone access on Linux via WebKitGTK
WebKitGTK denies getUserMedia by default. This adds webkit2gtk as a
Linux dependency and configures the webview to enable media streams
and auto-grant UserMediaPermissionRequest for microphone access.

Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-02-27 06:49:08 +01:00
IvanandClaude Opus 4.6 5ad67d7ecb fix: disable DMABUF renderer for NVIDIA GPUs on Linux
WebKitGTK fails to create GBM buffers with NVIDIA proprietary drivers,
resulting in an empty/blank Tauri window. Set WEBKIT_DISABLE_DMABUF_RENDERER=1
in the dev target to work around this.

Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-02-27 06:32:02 +01:00
Vaibhavee Singh 6cc96c2614 Fix #134: Add validation for duplicate profile names
- Add validation in create_profile() to check for existing names before insert
- Add validation in update_profile() to prevent renaming to duplicate names
- Improve error handling in API endpoints with user-friendly messages
- Add comprehensive test suite for duplicate name validation
- Update CHANGELOG.md with fix details

This fix prevents database constraint violations and provides clear
error messages when users attempt to create or update profiles with
names that already exist in the database.
2026-02-24 10:17:39 +05:30
Jamie Pine 38bf96ff20 fix: pin numba for release CI wheel compatibility 2026-02-23 12:18:34 -08:00
Jamie Pine 0b14cb1b2c Bump version: 0.1.12 → 0.1.13 2026-02-23 11:24:46 -08:00
Jamie Pine 4d24e69012 docs: point download links to latest release 2026-02-23 11:23:30 -08:00
Jamie PineandGitHub 90436e428d Merge pull request #77 from ManuLG/fix/broken-confirmation-modals
fix: await for confirmation before deleting voices and channels
2026-02-23 11:13:12 -08:00
Jamie PineandGitHub e4bb288904 Merge pull request #93 from iJaack/fix/mlx-apple-silicon-binary
fix(mlx): bundle native libs and broaden error handling for Apple Silicon
2026-02-23 11:12:34 -08:00
Jamie PineandGitHub 6f8bc7f23b Merge pull request #95 from CelebrityPunks/fix/model-size-selection-ignored
Fix: selecting 0.6B model still downloads and uses 1.7B
2026-02-23 11:12:12 -08:00
Jamie PineandGitHub baca111d50 Merge branch 'main' into fix/model-size-selection-ignored 2026-02-23 11:12:05 -08:00
Jamie PineandGitHub cc298fe6d8 Merge pull request #79 from martyniukyurii/fix/unicode-content-disposition
fix: handle non-ASCII filenames in Content-Disposition headers
2026-02-23 11:09:36 -08:00
Jamie PineandGitHub 46b8f6b882 Merge pull request #78 from tomasmach/fix/getUserMedia-undefined-check
fix: guard getUserMedia call against undefined mediaDevices in non-secure contexts
2026-02-23 11:09:23 -08:00
Claudio Casale edfc6e99fe feat: add Docker + web deployment support 2026-02-23 12:52:03 +01:00
Makinde d00e28ffda Fix: Prevent crashes when HuggingFace is unreachable
Implements offline mode patch for API stability issues:

- Add hf_offline_patch.py to monkey-patch huggingface_hub
- Force cache-only lookups before mlx_audio imports
- Create symlink from original Qwen repo to MLX community version
  when only MLX version is cached

This fixes:
- Issue #150: Internet required even with cached models
- Issue #151: API crashes when HF network fails

The patch ensures that if models are locally cached, no network
requests are made to HuggingFace during speech generation.
2026-02-22 01:57:02 -08:00
Jamie PineandGitHub 162cf4fb84 Merge pull request #122 from white1107/fix/web-tailwind-plugin
fix(web): add @tailwindcss/vite plugin to web config
2026-02-21 13:46:30 -08:00
Jamie PineandGitHub 68558243d9 Merge pull request #126 from lemassykoi/main
Create requirements.txt
2026-02-21 13:46:07 -08:00
Jamie PineandGitHub 8d5ad926f9 Merge pull request #128 from mrigankad/fix/voicebox-bugs
fix: resolve multiple issues (#96, #119, #111, #108, #121, #125, #127)
2026-02-21 13:45:19 -08:00
Jamie PineandGitHub 334f037dce Merge pull request #146 from xPolar/landing/spacebot-banner
Add Spacebot banner to landing page
2026-02-21 13:41:31 -08:00
xPolar f6522eea80 Add Spacebot banner to landing page
Adds a persistent top-of-page banner linking to spacebot.sh,
another project by the creator of Voicebox. Uses existing design
tokens for a consistent look.
2026-02-21 13:37:44 -08:00
lemassykoiandAmp 7615a08f81 ci: add Windows-only build workflow without signing
Amp-Thread-ID: https://ampcode.com/threads/T-019c7c3e-072f-7109-86a7-072a6b309891
Co-authored-by: Amp <[email protected]>
2026-02-20 23:06:45 +01:00
Rahul Sharma 28a4fd4824 feat: add network access toggle to server settings
Exposes the existing remote server mode through a checkbox in Server
Connection settings. When enabled, the server binds to 0.0.0.0 instead
of 127.0.0.1, making it accessible from other devices on the network.

The plumbing already existed (Rust sidecar passes --host 0.0.0.0 when
remote=true, serverStore has mode state, Python backend accepts --host),
but the UI hardcoded startServer(false). This wires it up.

Closes #104
2026-02-21 00:39:39 +05:30
lemassykoiandAmp 31ea3c68a5 fix: remove silent browser fallback that bypasses save dialog path
Amp-Thread-ID: https://ampcode.com/threads/T-019c7c3e-072f-7109-86a7-072a6b309891
Co-authored-by: Amp <[email protected]>
2026-02-20 19:27:41 +01:00
Mriganka 54d72ddfd0 fix: resolve multiple issues (#96, #119, #111, #108, #121, #125, #127) 2026-02-20 23:23:38 +05:30
Clément PAPPALARDOandGitHub d4794f78e1 Create requirements.txt 2026-02-20 17:14:14 +01:00
white1107 aa7c9a9a8d fix(web): add @tailwindcss/vite plugin to web config
The web version was missing the Tailwind CSS Vite plugin, causing
CSS to not load at all. This adds the same plugin configuration
that exists in the tauri version.

Fixes #121
2026-02-20 20:11:27 +09:00
AbrahamandClaude Opus 4.6 ca6ed0998a Fix model size selection ignored when generating speech
The /generate endpoint created the voice prompt before loading the
user's requested model size. Since create_voice_prompt() internally
calls load_model_async(None), it fell back to the hardcoded default
of "1.7B", causing the 1.7B model to be downloaded even when the
user explicitly selected 0.6B.

This reorders the operations so the requested model is loaded first,
ensuring create_voice_prompt() and generate() use the correct model.

Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-02-18 09:41:44 -08:00
Eva 829d4d6d5b fix(mlx): bundle native libs and broaden error handling for Apple Silicon
The distributed macOS aarch64 binary shipped without MLX acceleration despite
the model and backend code supporting it. Two root causes:

1. **OSError not caught in platform_detect.py**
   PyInstaller bundles isolate the filesystem, so when MLX tries to load its
   Metal shader libraries (.metallib) it raises OSError, not ImportError.
   platform_detect.get_backend_type() only caught ImportError, causing a
   silent fallback to PyTorch even on Apple Silicon hardware.
   Fix: broaden the except clause to (ImportError, OSError, RuntimeError)
   and import mlx.core instead of mlx (forces native lib loading eagerly).

2. **collect_data_files used instead of collect_all for MLX**
   build_binary.py and voicebox-server.spec used --collect-data /
   collect_data_files for mlx and mlx_audio. This copies Python source and
   pure-Python data, but NOT native shared libraries (.dylib, .metallib).
   Fix: switch to --collect-all / collect_all which captures binaries too,
   then pass them to Analysis(binaries=...) in the spec.

Result: macOS Apple Silicon users now get MLX inference (~4-5x faster than
PyTorch CPU), matching the performance documented in the README.
2026-02-18 16:51:48 +01:00
David Gil 80c87c8e2c test: add CORS origin restriction tests
20 tests covering:
- All 6 default local origins are allowed
- Arbitrary external origins are blocked
- Preflight (OPTIONS) requests respect the allowlist
- VOICEBOX_CORS_ORIGINS env var extends the allowlist
- Edge cases: empty env, whitespace trimming, trailing commas

Tests use a minimal FastAPI app mirroring the real CORS config,
so they run without ML dependencies (torch, numpy, etc.).
2026-02-17 22:04:25 +01:00
David Gil 427d811954 security: restrict CORS to known local origins instead of wildcard
The wildcard `allow_origins=["*"]` allows any website the user visits to
make requests to the local voicebox backend, potentially triggering TTS
generation or reading voice profiles without consent.

Restrict to the known Tauri webview and Vite dev server origins by
default. Users running in remote server mode can set
VOICEBOX_CORS_ORIGINS to allow additional origins.
2026-02-17 21:58:08 +01:00
YuriiandCursor 0be7975db5 fix: handle non-ASCII filenames in Content-Disposition headers
The export endpoints (export-audio, export generation, export profile,
export story) crash with `'latin-1' codec can't encode characters` when
the generated text or profile/story name contains non-ASCII characters
(e.g. Cyrillic, Chinese, Arabic).

Root cause: Python's `str.isalnum()` passes Unicode letters through to
the filename, but HTTP headers are encoded as latin-1 by the ASGI server,
which cannot represent characters outside the 0-255 range.

Fix: introduce `_safe_content_disposition()` helper that builds a
standards-compliant header with an ASCII-only `filename` fallback and a
RFC 5987 `filename*=UTF-8''...` parameter for Unicode-capable clients.

Fixes #68

Co-authored-by: Cursor <[email protected]>
2026-02-17 12:58:42 +04:00
tomasmach 40e4af828a fix: guard getUserMedia call against undefined mediaDevices in non-secure contexts 2026-02-17 09:28:23 +01:00
Manuel Lorenzo 0e57826ea5 fix: await for confirmation before deleting voices and channels 2026-02-17 00:29:52 +01:00
Spacedrive Mac Mini 2 eb2cd861b1 chore: update Cargo.lock version to 0.1.12 2026-02-10 06:59:41 -08:00
Jamie PineandGitHub 701cc647a7 Merge pull request #57 from selop/chore/readme
chore: updates repo URL in README
2026-02-06 05:08:24 -08:00
Sergej Lopatkin be6ccaf044 chore: updates repo URL in README
Updates the repository URL in the README to point to the correct fork.

Adds a prerequisite for XCode on macOS for development.
2026-02-06 13:22:59 +01:00
Jamie Pine 2e6efa00a2 Refactor documentation structure and dependencies for migration to Fumadocs
- Updated `.gitignore` to include new build and generated content directories.
- Removed outdated Mintlify configuration files and documentation.
- Introduced new `MIGRATION.md` to outline the transition from Mintlify to Fumadocs.
- Added `mdx-components.tsx` for MDX component configuration and compatibility.
- Updated `package.json` and `next.config.mjs` for new dependencies and Next.js configuration.
- Created `source.config.ts` for content source configuration.
- Added OpenAPI specification in `openapi.json` for API documentation.
- Removed legacy files and adjusted project structure to align with Fumadocs conventions.
2026-02-02 23:29:35 -08:00
Jamie Pine 788a04f265 Merge branch 'main' into better-docs 2026-02-02 23:18:06 -08:00
Jamie PineandGitHub 1040625a88 Merge pull request #44 from selop/feature/delivery-instructions
Enhances floating generate box UX
2026-02-02 17:58:19 -08:00
Sergej Lopatkin 6f4503b521 Enhances floating generate box UX
- Adds tooltips on hover for buttons of the generate box
- Replaces the message square icon with a sliders icon for the instruction mode toggle.
- Adds a tooltip to the instruction mode toggle button.
- Updates the placeholder text for the input field.
2026-02-02 22:19:54 +01:00
Sergej LopatkinandGitHub f5b6edc2e7 Merge pull request #1 from jamiepine/main
update fork
2026-02-02 22:19:30 +01:00
Jamie PineandGitHub 8197f0724c Merge pull request #40 from Spyabo/fix/audio-export-path-resolution
Fix: audio export path resolution
2026-02-02 06:54:39 -08:00
Reese Wright d40f7d2676 refactor: improve path resolution readability 2026-02-02 14:54:05 +00:00
Reese Wright 99fbcca7f4 update CHANGELOG for audio export fix 2026-02-02 14:34:39 +00:00
Reese Wright 04f9880c9a fix audio export path resolution 2026-02-02 14:26:34 +00:00
Jamie Pine b9c858295d Update Voicebox description as an alternative to ElevenLabs, rather than Ollama 2026-02-01 00:45:47 -08:00
Jamie Pine 610f64c762 fix linux compile 2026-01-31 07:44:28 -08:00
Jamie Pine 220333b3bb corrections 2026-01-31 02:15:45 -08:00
Jamie Pine e194e95512 corrections 2026-01-31 02:14:37 -08:00
Jamie Pine e796412c2c corrections 2026-01-31 02:13:42 -08:00
Jamie Pine cb541521d2 Update TTS Provider Architecture status to v0.1.13 2026-01-31 02:11:41 -08:00
Jamie Pine 2bc243f93e Add TTS Provider Architecture plan
Solves GitHub 2GB limit + frequent update UX issues by splitting app into:
- Main app (~150MB): UI + backend logic + Whisper
- TTS Providers (plugins): Separate downloadable binaries
  - pytorch-cpu (~300MB)
  - pytorch-cuda (~2.4GB)
  - mlx (~800MB, macOS)
  - remote (connect to external server)
  - openai (API wrapper)

Benefits:
- Main app under GitHub 2GB limit
- Updates don't require re-downloading providers
- User choice of compute backend
- External provider support for teams/cloud
- Future-proof extensibility
2026-01-31 02:09:42 -08:00
Jamie Pine 0209008d73 disable cuda for 0.1.12 2026-01-31 01:46:14 -08:00
Jamie Pine 5cb54ee03c Update API documentation and enhance server configuration
- Added server configurations for local and production environments in `main.py`.
- Removed outdated authentication and generation API documentation files.
- Updated documentation structure to reflect the removal of deprecated API endpoints.
- Adjusted links in the quick start and developer setup documentation to point to the new API reference.
- Enhanced global CSS styles for improved theming support.
2026-01-31 01:45:42 -08:00
Jamie Pine 0922845101 disable cuda for 0.1.12 2026-01-31 01:44:34 -08:00
Jamie Pine 64dd29d35a Add initial setup for Fumadocs documentation migration
- Created new directory structure for documentation under `/docs2`.
- Added `.gitignore` to exclude build artifacts and dependencies.
- Introduced `package.json`, `next.config.mjs`, and `postcss.config.mjs` for project configuration.
- Implemented MDX components in `mdx-components.tsx` for rendering documentation.
- Migrated existing documentation content and created new files for auto-updater and other features.
- Established compatibility layer for Mintlify components in `mintlify-compat.tsx`.
- Set up OpenAPI documentation in `openapi.json`.
- Updated README and migration guide to reflect new structure and usage instructions.
- Ensured all components and pages are ready for development and deployment with Fumadocs.
2026-01-30 23:32:45 -08:00
Jamie Pine 9bde534860 Bump version: 0.1.11 → 0.1.12 2026-01-30 21:23:07 -08:00
Jamie PineandGitHub 97eb570b28 Merge pull request #25 from jamiepine/fix-dl-notification-when-generating-from-already-cached-model
Fix dl notification when generating from already cached model
2026-01-30 21:20:25 -08:00
Jamie PineandGitHub 7d0557a099 Merge pull request #27 from jamiepine/model-dl-fix
Enhance model caching checks and progress tracking for downloads
2026-01-30 21:19:52 -08:00
Jamie PineandGitHub 20851ccc2b Merge pull request #24 from jamiepine/fix-multi-sample
Fix multi sample
2026-01-30 17:07:53 -08:00
Jamie Pine e5f4606a6c Update CircleButton component to include default button type
- Added a default `type` prop set to 'button' in the CircleButton component to ensure proper button behavior.
- Enhanced the component's flexibility by allowing the type to be overridden through props.
2026-01-30 17:07:35 -08:00
Jamie Pine 146ef5aaeb Add delete confirmation dialogs in HistoryTable and SampleList components
- Implemented delete confirmation dialogs for both HistoryTable and SampleList components to enhance user experience and prevent accidental deletions.
- Added state management for handling the selected item to be deleted and the visibility of the delete dialog.
- Refactored delete handling functions to utilize the new dialog confirmation flow, improving code clarity and maintainability.
2026-01-30 17:06:12 -08:00
Jamie Pine 971604d14f Implement profile cache management in audio processing
- Added `clear_profile_cache` function to manage cache files for specific profiles.
- Integrated cache clearing in `add_profile_sample`, `delete_profile`, and `delete_profile_sample` functions to ensure stale audio caches are invalidated after modifications.
- Enhanced `clear_voice_prompt_cache` to also delete combined audio files, improving overall cache management.
2026-01-30 16:50:24 -08:00
Jamie PineandGitHub 7fcca09f24 Merge pull request #23 from jamiepine/audio-export-entitlement-fix
Audio export entitlement fix
2026-01-30 15:08:50 -08:00
388 changed files with 39008 additions and 14004 deletions
+120
View File
@@ -0,0 +1,120 @@
---
name: add-tts-engine
description: Use this skill to add a new TTS engine to Voicebox. It walks through dependency research, backend implementation, frontend wiring, PyInstaller bundling, and frozen-build testing. Always start with Phase 0 (dependency audit) before writing any code.
---
# Add TTS Engine
## Goal
Integrate a new text-to-speech engine into Voicebox end-to-end: dependency research, backend protocol implementation, frontend UI wiring, PyInstaller bundling, and frozen-build verification. The user should only need to test the final build locally.
## Reference Doc
The full phased guide lives at `docs/content/docs/developer/tts-engines.mdx`. **Read this file in its entirety before starting.** It contains:
- Phase 0: Dependency research (mandatory before writing code)
- Phase 1: Backend implementation (`TTSBackend` protocol)
- Phase 2: Route and service integration (usually zero changes)
- Phase 3: Frontend integration (5 files)
- Phase 4: Dependencies (`requirements.txt`, justfile, CI, Docker)
- Phase 5: PyInstaller bundling (`build_binary.py` + `server.py`)
- Phase 6: Common upstream workarounds
- Implementation checklist (gate between phases)
## Workflow
### 1. Read the guide
```bash
# Read the full TTS engines doc
cat docs/content/docs/developer/tts-engines.mdx
```
Internalize all phases, especially Phase 0 and Phase 5. The v0.2.3 release was three patch releases because Phase 0 was skipped.
### 2. Dependency research (Phase 0)
Clone the model library into a temporary directory and audit it. Do NOT skip this.
```bash
mkdir /tmp/engine-research && cd /tmp/engine-research
git clone <model-library-url>
```
Run the grep searches from Phase 0.2 in the guide against the cloned source and its transitive dependencies. Produce a written dependency audit covering:
1. PyPI vs non-PyPI packages
2. PyInstaller directives needed (`--collect-all`, `--copy-metadata`, `--hidden-import`)
3. Runtime data files that must be bundled
4. Native library paths that need env var overrides in frozen builds
5. Monkey-patches needed (`torch.load`, float64, MPS, HF token)
6. Sample rate
7. Model download method (`from_pretrained` vs `snapshot_download` + `from_local`)
Test model loading and generation on CPU in the throwaway venv before proceeding.
### 3. Implement (Phases 1–4)
Follow the guide's phases in order. Key files to modify:
**Backend (Phase 1):**
- Create `backend/backends/<engine>_backend.py`
- Register in `backend/backends/__init__.py` (ModelConfig + TTS_ENGINES + factory)
- Update regex in `backend/models.py`
**Frontend (Phase 3):**
- `app/src/lib/api/types.ts` — engine union type
- `app/src/lib/constants/languages.ts` — ENGINE_LANGUAGES
- `app/src/components/Generation/EngineModelSelector.tsx` — ENGINE_OPTIONS, ENGINE_DESCRIPTIONS
- `app/src/lib/hooks/useGenerationForm.ts` — Zod schema, model-name mapping
- `app/src/components/ServerSettings/ModelManagement.tsx` — MODEL_DESCRIPTIONS
**Dependencies (Phase 4):**
- `backend/requirements.txt`
- `justfile` (setup-python, setup-python-release targets)
- `.github/workflows/release.yml`
- `Dockerfile` (if applicable)
### 4. PyInstaller bundling (Phase 5)
Register the engine in `backend/build_binary.py`:
- `--hidden-import` for the backend module and model package
- `--collect-all` for packages using `inspect.getsource`, shipping data files, or native libraries
- `--copy-metadata` for packages using `importlib.metadata`
If the engine has native data paths, add `os.environ.setdefault()` in `backend/server.py` inside the `if getattr(sys, 'frozen', False):` block.
### 5. Verify in dev mode
```bash
just dev
```
Test the full chain: model download → load → generate → voice cloning.
### 6. Use the checklist
Walk through the Implementation Checklist at the bottom of `tts-engines.mdx`. Every item must be checked before handing the build to the user.
## Key Lessons (from v0.2.3)
These are the most common failure modes. Phase 0 research catches all of them:
| Pattern | Symptom in Frozen Build | Fix |
|---------|------------------------|-----|
| `@typechecked` / `inspect.getsource()` | "could not get source code" | `--collect-all <package>` |
| Package ships pretrained model files | `FileNotFoundError` for `.pth.tar`, `.yaml` | `--collect-all <package>` |
| C library with hardcoded system paths | `FileNotFoundError` for `/usr/share/...` | `--collect-all` + env var in `server.py` |
| `importlib.metadata.version()` | "No package metadata found" | `--copy-metadata <package>` |
| `torch.load` without `map_location` | CUDA device not available on CPU build | Monkey-patch `torch.load` |
| `torch.from_numpy` on float64 data | dtype mismatch RuntimeError | Cast to `.float()` |
| `token=True` in HF download calls | Auth failure without stored HF token | Use `snapshot_download(token=None)` + `from_local()` |
## Notes
- The route and service layers have zero per-engine dispatch points. `main.py` requires zero changes.
- The model config registry in `backends/__init__.py` handles all dispatch automatically.
- Use `get_torch_device()` and `model_load_progress()` from `backends/base.py` — don't reimplement device detection or progress tracking.
- Always test with a **clean HuggingFace cache** (no pre-downloaded models from dev).
- Do NOT push or create a release. Hand the build to the user for local testing.
@@ -0,0 +1,94 @@
---
name: draft-release-notes
description: Use this skill to draft or update the [Unreleased] section of CHANGELOG.md from the actual changes since the last tag. Run this at any point during development to keep a working copy of the release narrative. Does NOT bump versions or create tags.
---
# Draft Release Notes
## Goal
Update the `[Unreleased]` section at the top of `CHANGELOG.md` with a narrative release story based on the real changes since the last tag. This is a **non-destructive working copy** — run it as many times as you want during development.
## Workflow
1. **Identify the last release tag and gather changes.**
```bash
LAST_TAG=$(git tag --list "v*" --sort=-v:refname | head -n 1)
echo "Last tag: $LAST_TAG"
```
Then collect raw material from three sources:
a. **Commit log since last tag:**
```bash
git log --oneline "$LAST_TAG"..HEAD
```
b. **GitHub-generated release notes preview** (PR titles, new contributors):
```bash
gh api repos/:owner/:repo/releases/generate-notes \
-f tag_name="vNEXT" \
-f target_commitish="$(git rev-parse HEAD)" \
-f previous_tag_name="$LAST_TAG" \
--jq '.body'
```
c. **Diff stat for theme analysis:**
```bash
git diff --stat "$LAST_TAG"..HEAD
```
2. **Draft the release narrative.**
Write markdown for the `[Unreleased]` section following the format below. Do not include the `## [Unreleased]` heading itself — just the body content.
3. **Update CHANGELOG.md.**
Replace everything between `## [Unreleased]` and the next `## [` heading with the new draft. Preserve the HTML comment header and all existing release sections below.
The `[Unreleased]` section must always exist and always be the first section after the header comments.
4. **Do NOT commit, tag, or bump versions.** Just leave the file modified in the working tree.
## Release Story Format
Structure the `[Unreleased]` section like this:
```markdown
## [Unreleased]
<One strong opening paragraph: what this release is about and why it matters.
Tie it to concrete shipped changes. No vague hype.>
<One paragraph on major technical shifts, if applicable.>
### <Feature/Theme Group>
- Bullet points with specifics
- Reference PRs where available: ([#123](https://github.com/jamiepine/voicebox/pull/123))
### <Another Group>
- ...
### Bug Fixes
- ...
```
### Style Guidelines
- **Factual and specific.** Every claim should trace to a real commit or PR.
- **Narrative over list.** Lead with paragraphs that tell the story, then support with bullets.
- **Group by theme, not by commit.** Cluster related changes under descriptive headings.
- **Reference PRs** where they exist, but don't fabricate them.
- **Skip trivial chores** (typo fixes, CI tweaks) unless they're the bulk of the release.
- **Match the voice of existing releases** — look at the v0.2.1 and v0.2.3 entries in CHANGELOG.md for tone reference.
## When There Are No Changes
If `git log "$LAST_TAG"..HEAD` is empty, leave the `[Unreleased]` section empty (just the heading) and tell the user there's nothing to draft.
## Notes
- This skill only touches the `[Unreleased]` section. It never modifies stamped release sections.
- The agent can be asked to run this skill at any point — mid-feature, before a PR, or right before cutting a release.
- The `release-bump` skill depends on this draft being up to date before it finalizes.
+124
View File
@@ -0,0 +1,124 @@
---
name: release-bump
description: Use this skill to finalize a release. It stamps the [Unreleased] changelog section with a version and date, runs bumpversion to update all version files, and creates the release commit and tag. Only run this when you're ready to ship.
---
# Release Bump
## Goal
Finalize the changelog draft, bump the version across all tracked files, and create a tagged release commit. After this skill runs, the repo has a clean release commit and tag ready to push.
## Prerequisites
- `gh` CLI installed and authenticated (`gh auth status`).
- `bumpversion` installed (`pip install bumpversion` or available in the project venv).
- The `[Unreleased]` section of `CHANGELOG.md` should already contain the release narrative. If it's empty or stale, run the `draft-release-notes` skill first.
## Workflow
1. **Verify the working tree is clean** (except `CHANGELOG.md` which may have the draft).
```bash
git status --porcelain
```
Only `CHANGELOG.md` (and optionally `.agents/` files) should be modified. If there are other uncommitted changes, stop and ask the user to commit or stash them first.
2. **Determine the bump level.**
Ask the user if not specified: `patch`, `minor`, or `major`. Check the current version:
```bash
grep '^current_version' .bumpversion.cfg
```
3. **Stamp the changelog.**
Read the current `[Unreleased]` content from `CHANGELOG.md`. Compute the new version (based on bump level and current version). Then:
a. Replace the `## [Unreleased]` section body with an empty placeholder.
b. Insert a new stamped section immediately after `## [Unreleased]`:
```markdown
## [Unreleased]
## [X.Y.Z] - YYYY-MM-DD
<the content that was in [Unreleased]>
```
c. Update the reference links at the bottom of the file:
- Change the `[Unreleased]` link to compare against the new tag
- Add a new link for the new version
```markdown
[Unreleased]: https://github.com/jamiepine/voicebox/compare/vX.Y.Z...HEAD
[X.Y.Z]: https://github.com/jamiepine/voicebox/compare/vPREVIOUS...vX.Y.Z
```
4. **Stage the changelog.**
```bash
git add CHANGELOG.md
```
5. **Run bumpversion.**
```bash
bumpversion --allow-dirty <patch|minor|major>
```
The `--allow-dirty` flag is needed because `CHANGELOG.md` is already staged. bumpversion will:
- Update version strings in all tracked files (see `.bumpversion.cfg`)
- Create a commit with message `Bump version: X.Y.Z -> A.B.C`
- Create a tag `vA.B.C`
The staged `CHANGELOG.md` will be included in this commit automatically.
6. **Verify results.**
```bash
git show --name-only --stat HEAD
git tag --list "v*" --sort=-v:refname | head -n 5
```
Confirm the commit contains:
- `CHANGELOG.md`
- `.bumpversion.cfg`
- `tauri/src-tauri/tauri.conf.json`
- `tauri/src-tauri/Cargo.toml`
- `package.json`
- `app/package.json`
- `tauri/package.json`
- `landing/package.json`
- `web/package.json`
- `backend/__init__.py`
Confirm the new tag exists.
7. **Do NOT push** unless the user explicitly asks. Report the tag name and suggest:
```
Ready to push. When you're ready:
git push origin main --follow-tags
```
## Version Calculation Reference
Given current version `X.Y.Z`:
- `patch` -> `X.Y.(Z+1)`
- `minor` -> `X.(Y+1).0`
- `major` -> `(X+1).0.0`
## Error Recovery
- If bumpversion fails, the tag won't exist. Fix the issue and re-run — bumpversion is idempotent as long as the tag doesn't already exist.
- If you need to undo a release commit (before pushing): `git tag -d vX.Y.Z && git reset --soft HEAD~1`
- Never amend a release commit that has been pushed.
## Notes
- When the tag is pushed, the release CI (`.github/workflows/release.yml`) automatically extracts the matching version section from `CHANGELOG.md` and uses it as the GitHub Release body. No manual copy-paste needed.
- The release commit message is controlled by `.bumpversion.cfg` (`Bump version: X.Y.Z -> A.B.C`). Do not override it.
- If you need to manually update the GitHub Release body after the fact: `gh release edit vX.Y.Z --notes-file <(sed -n '/## \[X.Y.Z\]/,/## \[/p' CHANGELOG.md | head -n -1)`
+299
View File
@@ -0,0 +1,299 @@
---
name: triage-prs
description: Use this skill to triage the open PR queue before a release. Classifies every open PR into must-merge, candidate, superseded, or deferred; writes a working triage doc; and runs the merge loop end-to-end. Designed for the pre-release "PR speedrun" pass where a solo maintainer wants to clear the inbound backlog in a single session.
---
# Triage PRs
## Goal
Turn a backlog of open PRs into a shipped set of merges in a single focused session. Produce a tracked, resumable plan (`<VERSION>_PR_TRIAGE.md`), then work it — rebasing where needed, merging in isolation-safe batches, applying post-merge follow-ups, and closing superseded or partially-applicable PRs with credit to their authors.
This skill pairs with `draft-release-notes` and `release-bump`: triage first, then draft notes against the new main, then cut the release.
## When to use
- Before a minor or major release when 10+ open PRs have accumulated
- When you want to unblock merging without losing the narrative of what's landing
- When you know you can't personally review every PR deeply, but need to land the critical subset fast
## Prerequisites
- `gh` CLI authenticated against the repo
- A dedicated worktree for PR review (avoid contaminating `main` with checkouts of contributor branches)
- Clarity on the target version — the triage doc is named after it (e.g. `0.4.0_PR_TRIAGE.md`)
## Workflow
### 1. Set up an isolated PR-review worktree
```bash
git worktree list # check for stale ones first
git worktree prune
git worktree add ../voicebox-pr-review -b pr-review-<VERSION> main
```
Keep the main worktree for release-prep work (changelog drafts, direct-to-main follow-ups). Keep the review worktree for `gh pr checkout` — each checkout moves HEAD to a contributor branch, which you don't want to do in the main worktree.
### 2. Gather metadata for every open PR
```bash
gh pr list --state open --limit 50 --json \
number,title,author,isDraft,mergeable,mergeStateStatus,files,additions,deletions,reviewDecision,statusCheckRollup,maintainerCanModify \
--jq '.[] | {num: .number, title, author: .author.login, mergeable, state: .mergeStateStatus, canModify: .maintainerCanModify, changes: "+\(.additions)/-\(.deletions)", files: [.files[].path]}'
```
You want, for each PR:
- Size (`+additions/-deletions`)
- Mergeable state (`CLEAN`, `UNSTABLE`, `DIRTY` = conflicts, `UNKNOWN` = GitHub still computing)
- Whether maintainer edits are allowed on the branch (needed later if you rebase for the author)
- File paths touched (helps spot overlaps between PRs)
`UNKNOWN` is common right after a push to main — just try the merge and see.
### 3. Classify into tiers
Sort each PR into exactly one bucket:
**Tier 1 — Merge:** small, mergeable, fixes a real bug, clean CI, low review cost. One-liners, dependency relaxations, targeted safety hardening. These are the easy wins.
**Tier 2 — Candidate, review:** medium size (50-200 lines), touches more surface area, looks sound but needs a closer read. New user-facing features that fit the product direction.
**Supersede:** the fix or feature is already covered by something merged. Close with a comment pointing to the superseding PR. Check carefully — "similar title" isn't proof; compare the actual diffs.
**Defer to next release:** big features, dirty conflicts, draft PRs, anything touching the release pipeline in ways that would introduce risk. Don't merge these in a speedrun — they need dedicated focus.
### 4. Write the triage doc
Create `<VERSION>_PR_TRIAGE.md` in the PR-review worktree root. Structure:
```markdown
# <Repo> <VERSION> — PR Triage
Working doc for tracking which open PRs land in <VERSION>. Delete after release cut.
Last updated: <DATE>
## Progress
**Tier 1: 0 / N merged**
**Tier 2: 0 / M handled**
**Supersede triage: pending**
---
## Merge for <VERSION> — critical bug fixes
| PR | Status | Size | What it fixes | Why must-have |
|---|---|---|---|---|
| [#123](url) | [ ] | +5/-0 | ... | ... |
## Strong candidate — needs a quick review
| PR | Status | Size | Summary |
|---|---|---|---|
## Close as superseded
| PR | Status | Reason |
|---|---|---|
## Defer to <NEXT_VERSION>
- [#xxx](url) ... — reason
---
## Order of attack
1. Close superseded PRs (one-liner comments)
2. Merge tier-1 in dependency-free batches — check file paths don't overlap
3. Review tier-2 individually
4. Rerun `draft-release-notes` to pick up everything
5. Run `release-bump`
```
The **Progress** header is the most important part — it's your scoreboard and lets you resume cleanly if the session gets interrupted.
### 5. Work the loop — per PR
For each PR in the tier-1 / tier-2 list:
**a. Checkout in the review worktree:**
```bash
cd ../voicebox-pr-review
git checkout pr-review-<VERSION> # reset to neutral base
gh pr checkout <N>
```
**b. Read the *actual* commit, not `main..HEAD`:**
```bash
git show HEAD # the PR's actual changes
git show --stat HEAD # files touched + line counts
```
**Do NOT review via `git diff main..HEAD`** if the PR branch is older than main. That diff includes *every commit that landed on main after the PR was forked* as `-` (deletion) lines. A 3-line PR can look like a 700-line revert. This is the single easiest way to misjudge a PR.
**c. Evaluate concerns:** correctness, scope, interaction with already-merged work, version compatibility (e.g. can't use an API that requires a dependency version we don't yet pin).
**d. Rebase if the branch is behind main:**
```bash
git fetch origin main
git rebase origin/main
```
This is **essential** before squash-merging. GitHub's squash computes `diff(PR-head, merge-base)` — on a stale branch, that diff includes reverting every in-between commit. Rebasing moves the merge-base forward so the squash is clean.
**e. If maintainer edits are allowed, push the rebase back to the contributor's fork:**
```bash
git remote add <author> https://github.com/<author>/<repo>.git
git fetch <author> <branch> # get their ref first
git push <author> HEAD:<branch> --force-with-lease
```
This keeps GitHub's PR UI in sync with the rebased state and makes the merge clean from the GitHub side.
**f. Merge:**
```bash
gh pr merge <N> --squash
```
**g. Update the triage doc** — flip the checkbox to `✅ merged <sha>` (use the short SHA from `gh pr view <N> --json mergeCommit --jq '.mergeCommit.oid[0:7]'`). Update the Progress header.
### 6. Batch tiny fixes
PRs with ≤5 line changes, clean CI, non-overlapping file paths, and obviously-correct intent (e.g. one-line dependency relax, env var add, import path fix) can be merged in a single loop without the review-per-PR ceremony:
```bash
for pr in 425 384 416 429; do
echo "=== Merging PR $pr ==="
gh pr merge $pr --squash
done
```
Verify afterward that each landed cleanly:
```bash
for pr in 425 384 416 429; do
gh pr view $pr --json state,mergeCommit --jq "{pr: $pr, state, sha: .mergeCommit.oid[0:7]}"
done
```
### 7. Post-merge follow-ups
Sometimes a PR is worth merging despite a known minor issue (e.g. incomplete dtype map, stale sentinel cleanup). Don't block the merge; apply the follow-up as a normal branch + PR right after:
```bash
cd <main-worktree>
git pull --ff-only origin main
git checkout -b fix/<short-name>
# edit...
git commit -m "fix(<area>): <one-liner>"
git push -u origin fix/<short-name>
gh pr create --title "..." --body "Follow-up to #<N>. ..."
```
Record both SHAs in the triage doc (`✅ merged <pr-sha> + follow-up <pr>`).
**Direct-to-main exception:** only under an explicit, scoped policy (e.g. "release speedrun"). Don't default to it.
### 8. Supersede: close with a credit-pointing comment
```bash
gh pr close <N> --comment "Closing — superseded by merged #<M> which landed <brief description>. Thanks!"
```
Check the diffs first — "similar title" is not enough. If the PR is *partially* superseded (the diagnosis is right but only half the changes are still needed), do a partial-apply instead.
### 9. Partial-apply pattern
When a PR has both valuable and questionable changes bundled:
```bash
cd <main-worktree>
git pull --ff-only origin main
# Cherry-pick specific files from the PR branch
git checkout <pr-commit-sha> -- <file1> <file2>
# Review the staged changes, adjust as needed
git diff --cached
# Apply any surgical edits to files you don't want to bulk-replace
# (e.g. the PR's file predates a recent main commit you need to preserve)
# Commit with a trailer crediting the original author
git commit -m "$(cat <<'EOF'
<subject>
<body explaining what was kept vs dropped>
Co-Authored-By: <author> <[email protected]>
EOF
)"
git push ... # branch + PR, unless under the direct-to-main exception
```
Then close the PR with a comment explaining what was applied and what was dropped, referencing the commit SHA.
### 10. Keep the doc current
Every merge, every close, every follow-up → update `<VERSION>_PR_TRIAGE.md`. The doc is your session log. If you're interrupted and resume tomorrow, the doc is the only source of truth for "where am I."
### 11. When triage is done
- Every PR in the doc has a terminal status (✅ merged / ✅ closed / deferred)
- Progress header shows N/N for each tier
- Next skill to run is `draft-release-notes` (to regenerate `[Unreleased]` against the new main), then `release-bump`
You can delete the triage doc after the release ships, or keep it in version history as a record.
## Gotchas
- **`main..HEAD` on a stale branch lies.** It shows everything main gained since the branch split as deletions. Always review via `git show HEAD` for the PR's actual commit.
- **Squash-merging an unrebased branch reverts in-between work.** The squash computes `diff(PR-head, merge-base)`. Rebase moves the merge-base forward.
- **`mergeable=UNKNOWN`** is transient — GitHub is recomputing after a push. Just try the merge.
- **Route ordering matters (FastAPI and similar):** `DELETE /history/failed` must be registered *before* `DELETE /history/{id}`, or the parameterized path will consume `"failed"` as an ID.
- **Apple's `-weak_framework` overrides `-framework`** for the same framework, regardless of order — use it via `cargo:rustc-link-arg=-Wl,-weak_framework,Name` when a dependency hard-links something optional.
- **Dependency version floors constrain what you can apply.** Before accepting a kwarg rename like `torch_dtype=` → `dtype=`, check the min-version pin supports it. Sometimes the right move is to cherry-pick half the PR.
- **`cpal::Stream` and similar `!Send` audio types** can't cross `await` points or `spawn_blocking`. Sometimes a "not-ideal but correct" sync wait is the best available fix; flag but don't block.
- **PyTorch nightly builds are not shippable for releases** — non-deterministic, can regress between runs. If a PR suggests switching to nightly to fix a GPU issue, prefer `TORCH_CUDA_ARCH_LIST=...+PTX` or wait for stable support instead.
## Canonical commands reference
```bash
# Bulk PR metadata
gh pr list --state open --limit 50 --json number,title,author,mergeable,mergeStateStatus,additions,deletions,maintainerCanModify,files
# Detailed single-PR view
gh pr view <N> --json body,author,headRefName,baseRefName,mergeable,maintainerCanModify,files,statusCheckRollup
# The actual commit, not the branch-vs-main diff
git show HEAD
git show --stat HEAD
gh pr diff <N>
# Rebase contributor branch onto current main
git fetch origin main && git rebase origin/main
# Push rebase back to contributor fork (maintainerCanModify=true required)
git remote add <author> https://github.com/<author>/<repo>.git
git fetch <author> <branch>
git push <author> HEAD:<branch> --force-with-lease
# Merge
gh pr merge <N> --squash
# Confirm merge SHA for triage doc
gh pr view <N> --json state,mergeCommit --jq '{state, sha: .mergeCommit.oid[0:7]}'
# Close superseded
gh pr close <N> --comment "Closing — superseded by merged #<M>. Thanks!"
```
## Notes
- **Never review a stale branch via `main..HEAD`.** This is the single most important line in this skill.
- **The triage doc is the session state.** Lose the doc, lose the session. Update it after every action.
- **Credit contributors even on partial-applies.** Use `Co-Authored-By:` trailers and close comments that link to the applied commit.
- **Don't let perfect be the enemy of shipped.** A fix that goes from "broken" to "works with a minor known issue" is a strict improvement. Flag the issue, file a follow-up, merge the fix.
+1 -1
View File
@@ -1,5 +1,5 @@
[bumpversion]
current_version = 0.1.11
current_version = 0.4.1
commit = True
tag = True
tag_name = v{new_version}
+45
View File
@@ -0,0 +1,45 @@
# Version control
.git
.github
.gitignore
# Desktop-only (not needed in web container)
tauri/
landing/
docs/
mlx-test/
scripts/
# Dependencies & build artifacts (rebuilt in Docker)
node_modules/
__pycache__/
*.pyc
*.pyo
*.egg-info/
dist/
build/
*.spec
# Data (will be bind-mounted)
data/
backend/data/
# IDE & OS
.vscode/
.idea/
*.swp
*.swo
.DS_Store
Thumbs.db
# Config files not needed in container
biome.json
.biomeignore
.bumpversion.cfg
.npmrc
Makefile
CONTRIBUTING.md
SECURITY.md
LICENSE
README.md
backend/README.md
+63
View File
@@ -0,0 +1,63 @@
name: Build Windows
on:
workflow_dispatch:
jobs:
build-windows:
permissions:
contents: write
runs-on: windows-latest
steps:
- uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.12"
cache: "pip"
- name: Install Python dependencies
run: |
python -m pip install --upgrade pip
pip install pyinstaller
pip install -r backend/requirements.txt
- name: Build Python server
shell: bash
run: |
cd backend
python build_binary.py
PLATFORM=$(rustc --print host-tuple)
mkdir -p ../tauri/src-tauri/binaries
cp dist/voicebox-server.exe ../tauri/src-tauri/binaries/voicebox-server-${PLATFORM}.exe
echo "Built voicebox-server-${PLATFORM}.exe"
- name: Setup Bun
uses: oven-sh/setup-bun@v2
- name: Install Rust stable
uses: dtolnay/rust-toolchain@stable
- name: Rust cache
uses: swatinem/rust-cache@v2
with:
workspaces: "./tauri/src-tauri -> target"
- name: Install dependencies
run: bun install
- uses: tauri-apps/tauri-action@v0
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
projectPath: tauri
tagName: v__VERSION__
releaseName: "voicebox v__VERSION__ (test build)"
releaseBody: "Test build for audio export fix"
releaseDraft: true
prerelease: true
args: ""
includeUpdaterJson: false
+26
View File
@@ -0,0 +1,26 @@
name: CI
on:
pull_request:
push:
branches:
- main
jobs:
frontend-quality:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Setup Bun
uses: oven-sh/setup-bun@v2
- name: Install dependencies
run: bun install --frozen-lockfile
- name: Typecheck app + web
run: bun run typecheck
- name: Build web smoke test
run: bun run build:web
+131 -40
View File
@@ -4,7 +4,7 @@ on:
workflow_dispatch:
push:
tags:
- 'v*'
- "v*"
jobs:
release:
@@ -14,22 +14,18 @@ jobs:
fail-fast: false
matrix:
include:
- platform: 'macos-latest'
args: '--target aarch64-apple-darwin'
python-version: '3.12'
backend: 'mlx'
- platform: 'macos-15-intel'
args: '--target x86_64-apple-darwin'
python-version: '3.12'
backend: 'pytorch'
# - platform: 'ubuntu-22.04'
# args: ''
# python-version: '3.12'
# backend: 'pytorch'
- platform: 'windows-latest'
args: ''
python-version: '3.12'
backend: 'pytorch'
- platform: "macos-latest"
args: "--target aarch64-apple-darwin"
python-version: "3.12"
backend: "mlx"
- platform: "macos-15-intel"
args: "--target x86_64-apple-darwin"
python-version: "3.12"
backend: "pytorch"
- platform: "windows-latest"
args: ""
python-version: "3.12"
backend: "pytorch"
runs-on: ${{ matrix.platform }}
@@ -37,10 +33,10 @@ jobs:
- uses: actions/checkout@v4
- name: Install dependencies (ubuntu only)
if: matrix.platform == 'ubuntu-22.04'
if: contains(matrix.platform, 'ubuntu') || contains(matrix.platform, 'namespace')
run: |
sudo apt-get update
sudo apt-get install -y libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf llvm-dev
sudo apt-get install -y libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf llvm-dev libasound2-dev
- name: Install LLVM (macOS)
if: matrix.platform == 'macos-latest' || matrix.platform == 'macos-15-intel'
@@ -53,24 +49,34 @@ jobs:
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
cache: 'pip'
cache: "pip"
- name: Install CPU-only PyTorch (Linux)
if: contains(matrix.platform, 'ubuntu') || contains(matrix.platform, 'namespace')
run: |
pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
- name: Install Python dependencies
run: |
python -m pip install --upgrade pip
pip install pyinstaller
pip install -r backend/requirements.txt
pip install --no-deps chatterbox-tts
pip install --no-deps hume-tada
- name: Install MLX dependencies (Apple Silicon only)
if: matrix.backend == 'mlx'
run: |
pip install -r backend/requirements-mlx.txt
- name: Install PyTorch with CUDA (Windows only)
if: matrix.platform == 'windows-latest'
run: |
pip install torch --index-url https://download.pytorch.org/whl/cu121 --force-reinstall --no-deps
pip install torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
# mlx-audio>=0.3.1 and mlx-lm>=0.31.1 both declare transformers>=5.x,
# which conflicts with our 4.57.x cap. The runtime APIs we use work
# fine on transformers 4.57.x in practice (verified in dev), so install
# them --no-deps. mlx-audio's other runtime deps (huggingface_hub,
# librosa, numpy, numba, pyloudnorm) are already in requirements.txt;
# the rest (sounddevice, miniaudio, protobuf, sentencepiece, pyyaml,
# jinja2) are pulled in by other engines.
pip install --no-deps mlx-lm==0.31.1
pip install --no-deps mlx-audio==0.4.1
- name: Build Python server (Linux/macOS)
if: matrix.platform != 'windows-latest'
@@ -106,7 +112,7 @@ jobs:
- name: Rust cache
uses: swatinem/rust-cache@v2
with:
workspaces: './tauri/src-tauri -> target'
workspaces: "./tauri/src-tauri -> target"
- name: Install dependencies
run: bun install
@@ -127,7 +133,30 @@ jobs:
p12-file-base64: ${{ secrets.APPLE_CERTIFICATE }}
p12-password: ${{ secrets.APPLE_CERTIFICATE_PASSWORD }}
- uses: tauri-apps/tauri-action@v0
- name: Extract release notes from CHANGELOG.md
id: changelog
shell: bash
run: |
# Get the version from the tag (strip leading 'v')
VERSION="${GITHUB_REF_NAME#v}"
# Extract the section for this version from CHANGELOG.md
# Matches from "## [X.Y.Z]" until the next "## [" heading
NOTES=$(sed -n "/^## \[${VERSION}\]/,/^## \[/{/^## \[${VERSION}\]/d;/^## \[/d;p;}" CHANGELOG.md)
# Fall back to a placeholder if the version isn't in the changelog
if [ -z "$(echo "$NOTES" | tr -d '[:space:]')" ]; then
NOTES="See the assets below to download and install this version."
fi
# Use multiline output syntax
{
echo "notes<<CHANGELOG_EOF"
echo "$NOTES"
echo "CHANGELOG_EOF"
} >> "$GITHUB_OUTPUT"
- uses: tauri-apps/[email protected]
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
TAURI_SIGNING_PRIVATE_KEY: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY }}
@@ -142,19 +171,81 @@ jobs:
with:
projectPath: tauri
tagName: v__VERSION__
releaseName: 'voicebox v__VERSION__'
releaseBody: |
## What's Changed
See the assets below to download and install this version.
### Installation
- **macOS (Apple Silicon)**: Download the `aarch64.dmg` file - uses MLX for fast native inference
- **macOS (Intel)**: Download the `x64.dmg` file - uses PyTorch
- **Windows**: Download the `.msi` installer
- **Linux**: Download the `.AppImage` or `.deb` package
The app includes automatic updates - future updates will be installed automatically.
releaseName: "voicebox v__VERSION__"
releaseBody: ${{ steps.changelog.outputs.notes }}
releaseDraft: true
prerelease: false
args: ${{ matrix.args }}
includeUpdaterJson: true
build-cuda-windows:
runs-on: windows-latest
permissions:
contents: write
steps:
- uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.12"
cache: "pip"
- name: Install Python dependencies
run: |
python -m pip install --upgrade pip
pip install pyinstaller
pip install -r backend/requirements.txt
pip install --no-deps chatterbox-tts
pip install --no-deps hume-tada
- name: Install PyTorch with CUDA 12.8
run: |
pip install torch --index-url https://download.pytorch.org/whl/cu128 --force-reinstall --no-deps
pip install torchaudio --index-url https://download.pytorch.org/whl/cu128 --force-reinstall --no-deps
- name: Verify CUDA support in torch
run: |
python -c "import torch; print(f'CUDA available in build: {torch.cuda.is_available()}'); print(f'CUDA version: {torch.version.cuda}')"
- name: Build CUDA server binary (onedir)
shell: bash
working-directory: backend
env:
# Include Blackwell (sm_120) via PTX forward compatibility.
# Pre-built PyTorch cu128 wheels ship native kernels for sm_80/86/89/90
# but not sm_120. Setting this env var causes torch.utils.cpp_extension
# (and any JIT-compiled kernels) to target Blackwell GPUs as well.
TORCH_CUDA_ARCH_LIST: "8.0;8.6;8.9;9.0;12.0+PTX"
run: python build_binary.py --cuda
- name: Package into server core + CUDA libs archives
shell: bash
run: |
python scripts/package_cuda.py \
backend/dist/voicebox-server-cuda/ \
--output release-assets/ \
--cuda-libs-version cu128-v1 \
--torch-compat ">=2.7.0,<2.11.0"
- name: Upload archives to GitHub Release
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v2
with:
files: |
release-assets/voicebox-server-cuda.tar.gz
release-assets/voicebox-server-cuda.tar.gz.sha256
release-assets/cuda-libs-cu128-v1.tar.gz
release-assets/cuda-libs-cu128-v1.tar.gz.sha256
release-assets/cuda-libs.json
draft: true
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload onedir as workflow artifact
uses: actions/upload-artifact@v4
with:
name: voicebox-server-cuda-windows
path: backend/dist/voicebox-server-cuda/
retention-days: 7
+15 -4
View File
@@ -35,10 +35,7 @@ target/
Thumbs.db
# Data (user-generated)
data/profiles/*
data/generations/*
data/projects/*
data/voicebox.db
data/
!data/.gitkeep
# Logs
@@ -52,8 +49,22 @@ logs/
# Generated files
app/openapi.json
tauri/src-tauri/binaries/*
tauri/src-tauri/gen/Assets.car
tauri/src-tauri/gen/voicebox.icns
tauri/src-tauri/gen/partial.plist
# PyInstaller
*.spec
# Windows artifacts
nul
# Temporary
tmp/
temp/
*.tmp
# E2E test artifacts
backend/tests/results/
backend/tests/fixtures/reference_voice.wav
backend/tests/fixtures/reference_voice.txt
+607 -71
View File
@@ -1,82 +1,618 @@
<!-- This file is compiled automatically during the release workflow. -->
<!-- Do not edit manually — your changes will be overwritten. -->
<!-- To update the draft: ask the agent to use the draft-release-notes skill. -->
<!-- To finalize a release: ask the agent to use the release-bump skill. -->
# Changelog
All notable changes to Voicebox will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [0.1.0] - 2026-01-25
### Added
#### Core Features
- **Voice Cloning** - Clone voices from audio samples using Qwen3-TTS (1.7B and 0.6B models)
- **Voice Profile Management** - Create, edit, and organize voice profiles with multiple samples
- **Speech Generation** - Generate high-quality speech from text using cloned voices
- **Generation History** - Track all generations with search and filtering capabilities
- **Audio Transcription** - Automatic transcription powered by Whisper
- **In-App Recording** - Record audio samples directly in the app with waveform visualization
#### Desktop App
- **Tauri Desktop App** - Native desktop application for macOS, Windows, and Linux
- **Local Server Mode** - Embedded Python server runs automatically
- **Remote Server Mode** - Connect to a remote Voicebox server on your network
- **Auto-Updates** - Automatic update notifications and installation
#### API
- **REST API** - Full REST API for voice synthesis and profile management
- **OpenAPI Documentation** - Interactive API docs at `/docs` endpoint
- **Type-Safe Client** - Auto-generated TypeScript client from OpenAPI schema
#### Technical
- **Voice Prompt Caching** - Fast regeneration with cached voice prompts
- **Multi-Sample Support** - Combine multiple audio samples for better voice quality
- **GPU/CPU/MPS Support** - Automatic device detection and optimization
- **Model Management** - Lazy loading and VRAM management
- **SQLite Database** - Local data persistence
### Technical Details
- Built with Tauri v2 (Rust + React)
- FastAPI backend with async Python
- TypeScript frontend with React Query and Zustand
- Qwen3-TTS for voice cloning
- Whisper for transcription
### Platform Support
- macOS (Apple Silicon and Intel)
- Windows
- Linux (AppImage)
---
## [Unreleased]
### Added
- **Makefile** - Comprehensive development workflow automation with commands for setup, development, building, testing, and code quality checks
- Includes Python version detection and compatibility warnings
- Self-documenting help system with `make help`
- Colored output for better readability
- Supports parallel development server execution
## [0.4.1] - 2026-04-18
### Changed
- **README** - Added Makefile reference and updated Quick Start with Makefile-based setup instructions alongside manual setup
A fast follow-up to 0.4.0 focused on making the new engines actually load in the production binary — plus generation cancellation, Linux system-audio capture, and the repo's first PR-time type check. Five first-time contributors shipped in this release.
---
0.4.0 introduced three new TTS engines, but the frozen PyInstaller binary tripped over several Python-ecosystem quirks that don't show up in the dev venv: `transformers` opening `.py` sources at runtime, `scipy.stats._distn_infrastructure` hitting a frozen-importer `NameError`, and `chatterbox-multilingual` failing to find its Chinese segmenter dictionary. This release patches all of those in one sweep.
## [Unreleased - Planned]
### Frozen-Binary Reliability ([#438](https://github.com/jamiepine/voicebox/pull/438))
- **Kokoro** now bundles `.py` sources alongside `.pyc` via `--collect-all kokoro` so `transformers`' `_can_set_attn_implementation` regex scan can read them — previously `FileNotFoundError: kokoro/modules.py` killed Kokoro loading in production builds
- **Chatterbox Multilingual** now bundles `spacy_pkuseg/dicts/default.pkl` and the package's native `.so` extensions via `--collect-all spacy_pkuseg` — previously the Chinese word segmenter crashed with `FileNotFoundError` on first load
- **scipy.stats._distn_infrastructure** — new runtime hook source-patches the trailing `del obj` (which raises `NameError` under PyInstaller's frozen importer because the preceding list comprehension evaluates empty) to `globals().pop('obj', None)`, unblocking `librosa` → `scipy.signal` → `scipy.stats` for every TTS engine that depends on librosa
- **transformers.masking_utils** — same runtime hook forces `_is_torch_greater_or_equal_than_2_6 = False` so the older `sdpa_mask_older_torch` path is selected; the 2.6+ path uses `TransformGetItemToIndex()`, a real `torch._dynamo` graph transform our permissive stub can't reproduce
- **torch._dynamo** — no-op stub replaces the real module before `transformers` imports it, preventing the `torch._numpy._ufuncs` import crash (`NameError: name 'name' is not defined`) that blocked Kokoro and every engine pulling in `flex_attention`
- `.spec` paths are now repo-relative instead of absolute, so the generated spec is portable across machines and CI
### Planned
- Real-time streaming synthesis
- Conversation mode with multiple speakers
- Voice effects (pitch shift, reverb, M3GAN-style)
- Timeline-based audio editor
- Additional voice models (XTTS, Bark)
- Voice design from text descriptions
- Project system for saving sessions
- Plugin architecture
### Generation
- **Cancel queued or running generations** ([#444](https://github.com/jamiepine/voicebox/pull/444)) — new `/generate/{id}/cancel` endpoint and a Stop button on the history row while generating. The serial queue now tracks per-ID state (queued / running / cancelled) so queued jobs are skipped before the worker picks them up and running jobs are `.cancel()`-ed mid-flight; `run_generation` catches `CancelledError` and marks the row `failed` with a "cancelled" error.
- **Legacy `data/` path prefix resolution** ([#440](https://github.com/jamiepine/voicebox/pull/440)) — generations stored with the old `data/` prefix under pre-0.4 installs now resolve correctly after the storage root moved, fixing 404s for historical audio.
---
### Model Migration
- Migration dialog no longer hangs when the cache is empty ([#439](https://github.com/jamiepine/voicebox/pull/439)) — the backend now emits a completion SSE event even when zero models are moved.
- Storage-change flow surfaces a toast when there's nothing to migrate ([#433](https://github.com/jamiepine/voicebox/pull/433)) instead of proceeding with a no-op move and restarting the server.
- Deleting all generations from a voice profile now deletes the associated version files and DB rows too ([#447](https://github.com/jamiepine/voicebox/pull/447)) — previously orphaned versions accumulated in storage.
### Platform
- **Linux system audio capture** ([#457](https://github.com/jamiepine/voicebox/pull/457)) — `cpal`'s ALSA backend doesn't expose PulseAudio/PipeWire monitor sources by name, so the previous device-name search never matched and silently fell back to the microphone. Detection now uses `pactl get-default-sink` + `pactl list short sources` and routes via `PULSE_SOURCE`, with the name-based search retained as a fallback when `pactl` is absent.
### Frontend CI
- First PR-time quality gate ([#418](https://github.com/jamiepine/voicebox/pull/418)) — new `.github/workflows/ci.yml` runs `bun run typecheck` + `bun run build:web` on every PR. Fixed pre-existing type issues that were being suppressed with `@ts-expect-error`, cleaned up a dep-array typo (`[platform.metadata.isTauricheckOnMountcheckForUpdates]`) in `useAutoUpdater`, and removed 100+ lines of dead `ModelItem` code from `ModelManagement.tsx`.
- Follow-up: widened `apiClient.migrateModels()` return type to include `moved` and `errors` so the storage-change handler typechecks against the real backend response ([#470](https://github.com/jamiepine/voicebox/pull/470)).
### Docs
- Clarified in the Quick Start + README that paralinguistic tags (`[laugh]`, `[sigh]`) only work with Chatterbox Turbo; other engines read them as literal text ([#450](https://github.com/jamiepine/voicebox/pull/450)).
### New Contributors
- [@Bortlesboat](https://github.com/Bortlesboat) — generation cancellation (#444)
- [@gaojulong](https://github.com/gaojulong) — migration dialog hang fix (#439)
- [@fuleinist](https://github.com/fuleinist) — migration no-op toast (#433)
- [@erionjuniordeandrade-a11y](https://github.com/erionjuniordeandrade-a11y) — frontend CI + type hardening (#418)
- [@estefrac](https://github.com/estefrac) — Linux pactl system-audio capture (#457)
## [0.4.0] - 2026-04-16
The biggest Voicebox release yet. Three new TTS engines bring the lineup to **seven** — HumeAI TADA, Kokoro 82M, and Qwen CustomVoice join Qwen3-TTS, LuxTTS, Chatterbox Multilingual, and Chatterbox Turbo. GPU support broadens to Intel Arc (XPU) and NVIDIA Blackwell (RTX 50-series), with runtime diagnostics that warn when your PyTorch build doesn't match your GPU. The CUDA backend is now split into independently versioned server and library archives, so upgrading no longer redownloads 4 GB of PyTorch/CUDA DLLs.
This release also marks a big community moment: **13 new contributors** shipped fixes and features in 0.4.0. Thirty-plus bug fixes target the most-reported issues in the tracker — numpy 2.x TTS crashes, Windows background-server reliability, macOS 11 launch failures, audio playback silence, Stories clip-splitting races, history status staleness, and more.
### New TTS Engines
#### HumeAI TADA — Expressive English & Multilingual ([#296](https://github.com/jamiepine/voicebox/pull/296))
- Added `tada-1b` (English) and `tada-3b-ml` (multilingual) backends
- Replaced `descript-audio-codec` with a lightweight DAC shim to cut dependencies
- Switched audio decoding to `soundfile` to sidestep `torchcodec` bundling issues
- Redirected gated Llama tokenizer lookups to an ungated mirror so model loading works out of the box
- Fixed tokenizer patch that was corrupting `AutoTokenizer` for other engines
- Fixed TorchScript error in frozen builds
#### Kokoro 82M — Fast Lightweight TTS ([#325](https://github.com/jamiepine/voicebox/pull/325))
- Added Kokoro 82M engine with a new voice profile type system that distinguishes preset voices from cloned profiles
- Profile grid now handles engine compatibility directly — removed redundant dropdown filtering
- Tightened Kokoro profile handling so preset voices can't be edited like cloned profiles
#### Qwen CustomVoice ([#328](https://github.com/jamiepine/voicebox/pull/328))
- Added `qwen-custom-voice` preset engine backed by Qwen3-TTS
- Enforced preset/profile engine compatibility across the generation flow
- Floating generator now shows all engines instead of silently filtering
### Voice Profile UX
Until 0.4, every engine in Voicebox was a cloning model, so every voice profile was usable with every engine and the profile grid just showed them all. Introducing Kokoro and Qwen CustomVoice — which work from preset voices rather than cloned samples — broke that assumption for the first time. An early cut on `main` filtered the grid by the selected engine, which left users running pre-release builds thinking their cloned voices had vanished whenever they switched to a preset-only engine.
This release ships the resolution before it ever reaches a tagged version:
- **Grey-out instead of filter** — all profiles are always visible; unsupported ones render dimmed with a compatibility hint at the bottom of the grid
- **Auto-switch on selection** — clicking a greyed-out profile selects it AND switches the engine to a compatible one, instead of silently doing nothing
- **Instruct toggle restored for Qwen CustomVoice** — the floating generate box now reveals a delivery-instructions input (tone, emotion, pace) when CustomVoice is selected. Hidden across the board while the new multi-engine lineup was stabilizing because most engines don't honor the kwarg; now conditionally exposed only for the one engine that was actually trained for instruction-based style control
- Supported profiles sort first; the grid scrolls the selected profile into view after engine/sort changes
- Fixed engine desync on tab navigation — the form now initializes its engine from the store
- Fixed the disabled-and-selected card click edge case by bouncing selection to re-trigger the auto-switch
- Cleaned up scroll effect timers (requestAnimationFrame + setTimeout) to prevent stale DOM writes on unmount or rapid selection changes
### GPU & Platform
#### Intel Arc (XPU) Support ([#320](https://github.com/jamiepine/voicebox/pull/320))
- First-class Intel Arc support across all PyTorch-based backends
- Device-aware seeding, XPU detection in the GPU status panel, and setup flow detection
- Reports correct device name and VRAM in settings
#### Blackwell / RTX 50-series Support ([#316](https://github.com/jamiepine/voicebox/pull/316), [#401](https://github.com/jamiepine/voicebox/pull/401))
- Upgraded the CUDA backend from cu126 → cu128 for RTX 50-series support
- Added `sm_120+PTX` to the CUDA build via `TORCH_CUDA_ARCH_LIST` for forward-compatibility with Blackwell architectures (closes 5 open reports: #386, #395, #396, #399, #400)
- GPU settings UI fixes around install/uninstall state
#### GPU Compatibility Diagnostics ([#367](https://github.com/jamiepine/voicebox/pull/367), adapted)
- New `check_cuda_compatibility()` compares the current device's compute capability against the bundled PyTorch's architecture list
- Health endpoint exposes a `gpu_compatibility_warning` field so the UI can surface mismatches
- Startup logs a `WARN` when the installed PyTorch build doesn't support the detected GPU
- GPU status label shows `[UNSUPPORTED - see logs]` — no more silent "no kernel image" failures
#### Split CUDA Backend ([#298](https://github.com/jamiepine/voicebox/pull/298))
- CUDA backend now ships as two independently versioned archives: a small server binary and a large libs archive (the ~4 GB of PyTorch/CUDA DLLs)
- Upgrading Voicebox no longer redownloads the libs archive when only the server binary changed
- Added `asyncio.Lock` around `download_cuda_binary()` so auto-update and manual download can't race on the same temp file ([#428](https://github.com/jamiepine/voicebox/pull/428))
- Updated `package_cuda.py` for PyInstaller 6.18 onedir layout
- Temp archives are always cleaned up on failure, even when the install aborts mid-extract
### Bug Fixes
#### Critical: TTS Generation
- **numpy 2.x `torch.from_numpy` crash** ([#361](https://github.com/jamiepine/voicebox/pull/361)) — torch compiled against numpy 1.x ABI fails silently when paired with numpy 2.x, causing `RuntimeError: Numpy is not available` / `Unable to create tensor` on every TTS request in bundled macOS Intel / Rosetta builds. Pinned `numpy<2.0` in requirements and added a PyInstaller runtime hook with a `ctypes.memmove` fallback as belt-and-suspenders. Hardened afterward to raise on unknown dtypes instead of silently reinterpreting bytes as float32.
#### Platform Reliability
- **Windows background server** ([#402](https://github.com/jamiepine/voicebox/pull/402)) — "keep server running after close" now actually keeps the server running. The HTTP `/watchdog/disable` request could lose the race against process exit on Windows; added a `.keep-running` sentinel file as a synchronous fallback, with stale-sentinel cleanup on startup to avoid orphan server processes
- **macOS 11 launch crash** ([#424](https://github.com/jamiepine/voicebox/pull/424)) — weak-linked ScreenCaptureKit so the app can launch on macOS < 12.3 instead of crashing at dyld resolution. Gated system audio capture behind a real `sw_vers` version check so unsupported systems cleanly advertise "not available" rather than crashing at runtime
- **macOS Intel (x86_64) setup** ([#416](https://github.com/jamiepine/voicebox/pull/416)) — relaxed `torch>=2.7.0` → `torch>=2.2.0`. PyTorch dropped pre-built x86_64 wheels after 2.2.2, so Intel Mac devs could no longer `pip install`. Now resolves to the latest compatible torch per platform
- **Offline model loading** ([#318](https://github.com/jamiepine/voicebox/pull/318)) — Qwen TTS and Whisper force offline mode when loading cached models, so startup works without network access
- **GUI startup with external server** ([#319](https://github.com/jamiepine/voicebox/pull/319)) — fixed GUI launch when pointed at a remote/external server, and added data refresh on server switch; hardened health validation and error handling
- **Qwen3-TTS cache split on Windows** (adapted from [#218](https://github.com/jamiepine/voicebox/pull/218)) — route `Qwen3TTSModel.from_pretrained` through `hf_constants.HF_HUB_CACHE` so the speech tokenizer and `preprocessor_config.json` resolve from a single cache root
- **Qwen3-TTS bundling** ([#305](https://github.com/jamiepine/voicebox/pull/305)) — bundle `qwen_tts` source files in the PyInstaller build to fix `inspect.getsource` errors in frozen builds
- **Backend import paths** ([#345](https://github.com/jamiepine/voicebox/pull/345)) — moved lazy imports to top-level with absolute paths to resolve the "Failed to Save" preset error caused by `ModuleNotFoundError` in production builds
- **Effects service import** ([#384](https://github.com/jamiepine/voicebox/pull/384)) — fixed `ModuleNotFoundError` on preset create/update by switching to relative imports (#349)
#### Audio & Playback
- **cpal stream silent playback** ([#405](https://github.com/jamiepine/voicebox/pull/405)) — `cpal::Stream` was dropped on function return immediately after `play()`, causing every playback to fall silent. Now holds the stream until either the buffer drains or the stop flag fires (#404)
#### Stories & History
- **Clip-splitting race** ([#403](https://github.com/jamiepine/voicebox/pull/403)) — rapid double-clicks on split could race through `split_story_item` with inconsistent state. Added `with_for_update()` row locking on the backend and an `isPending` guard on the frontend (#366)
- **History `status` staleness** ([#394](https://github.com/jamiepine/voicebox/pull/394)) — `GET /history/{id}` was hardcoding `status="completed"` regardless of the DB row, breaking any client polling for job completion. Now returns `status`, `error`, `engine`, `model_size`, and `is_favorited` from the actual row
- **"Clear failed" bulk button** ([#412](https://github.com/jamiepine/voicebox/pull/412)) — new `DELETE /history/failed` endpoint and a header strip showing `"N failed generations"` with a Clear button, complementing the per-row trash icon added in #321 (#410)
- **Delete failed generations** ([#321](https://github.com/jamiepine/voicebox/pull/321)) — added a trash icon next to the retry button so failed entries can be cleaned up without having to retry first
#### Security & Safety
- **Voice prompt cache hardening** ([#429](https://github.com/jamiepine/voicebox/pull/429)) — `torch.load(weights_only=True)` on cached voice prompts per PyTorch 2.6 recommendation; replaced string-based SPA path guard with `Path.is_relative_to()` for more robust path-traversal protection
#### Infrastructure & Docker
- **Docker web build** ([#344](https://github.com/jamiepine/voicebox/pull/344)) — include `CHANGELOG.md` in the Docker web build so the in-app changelog page works in Docker deployments
- **Docker numba cache** ([#425](https://github.com/jamiepine/voicebox/pull/425)) — set `NUMBA_CACHE_DIR` in docker-compose so numba can write its JIT cache in container runtime (#308)
- **Relative media paths** ([#332](https://github.com/jamiepine/voicebox/pull/332)) — media paths now stored relative to the configured data dir rather than resolved against CWD, so the data directory is portable between installs
### Developer Tooling
- New `triage-prs` agent skill — encodes the end-to-end PR-speedrun workflow (classification → triage doc → rebase → squash-merge → follow-ups) so future release cycles can reproduce it
- Rewrote the TTS engine guide with the patterns learned from adding TADA and Kokoro
- Added the API refactor plan and CUDA libs addon design doc
- Fixed broken links in the Get Started section ([#332](https://github.com/jamiepine/voicebox/pull/332))
### New Contributors
Huge thank you to everyone who contributed their first PR to Voicebox in this release:
[@liorshahverdi](https://github.com/liorshahverdi), [@nicoschtein](https://github.com/nicoschtein), [@ArfianID](https://github.com/ArfianID), [@aimaaaimaa](https://github.com/aimaaaimaa), [@maxmcoding](https://github.com/maxmcoding), [@Khalodddd](https://github.com/Khalodddd), [@LuisSambrano](https://github.com/LuisSambrano), [@shaun0927](https://github.com/shaun0927), [@malletfils](https://github.com/malletfils), [@mvanhorn](https://github.com/mvanhorn), [@kuishou68](https://github.com/kuishou68), [@txhno](https://github.com/txhno), [@MukundaKatta](https://github.com/MukundaKatta)
## [0.3.0] - 2026-03-17
This release rewrites the backend into a modular architecture, overhauls the settings UI into routed sub-pages, fixes audio player freezing, migrates documentation to Fumadocs, and ships a batch of bug fixes targeting the most-reported issues from the tracker.
The backend's 3,000-line monolith `main.py` has been decomposed into domain routers, a services layer, and a proper database package. A style guide and ruff configuration now enforce consistency. On the frontend, settings have been split into dedicated routed pages with server logs, a changelog viewer, and an about page. The audio player no longer freezes mid-playback, and model loading status is now visible in the UI. Seven user-reported bugs have been fixed, including server crashes during sample uploads, generation list staleness, cryptic error messages, and CUDA support for RTX 50-series GPUs.
### Settings Overhaul ([#294](https://github.com/jamiepine/voicebox/pull/294))
- Split settings into routed sub-tabs: General, Generation, GPU, Logs, Changelog, About
- Added live server log viewer with auto-scroll
- Added in-app changelog page that parses `CHANGELOG.md` at build time
- Added About page with version info, license, and generation folder quick-open
- Extracted reusable `SettingRow` component for consistent setting layouts
### Audio Player Fix ([#293](https://github.com/jamiepine/voicebox/pull/293))
- Fixed audio player freezing during playback
- Improved playback UX with better state management and listener cleanup
- Fixed restart race condition during regeneration
- Added stable keys for audio element re-rendering
- Improved accessibility across player controls
### Backend Refactor ([#285](https://github.com/jamiepine/voicebox/pull/285))
- Extracted all routes from `main.py` into 13 domain routers under `backend/routes/` — `main.py` dropped from ~3,100 lines to ~10
- Moved CRUD and service modules into `backend/services/`, platform detection into `backend/utils/`
- Split monolithic `database.py` into a `database/` package with separate `models`, `session`, `migrations`, and `seed` modules
- Added `backend/STYLE_GUIDE.md` and `pyproject.toml` with ruff linting config
- Removed dead code: unused `_get_cuda_dll_excludes`, stale `studio.py`, `example_usage.py`, old `Makefile`
- Deduplicated shared logic across TTS backends into `backends/base.py`
- Improved startup logging with version, platform, data directory, and database stats
- Fixed startup database session leak — sessions now rollback and close in `finally` block
- Isolated shutdown unload calls so one backend failure doesn't block the others
- Handled null duration in `story_items` migration
- Reject model migration when target is a subdirectory of source cache
### Documentation Rewrite ([#288](https://github.com/jamiepine/voicebox/pull/288))
- Migrated docs site from Mintlify to Fumadocs (Next.js-based)
- Rewrote introduction and root page with content from README
- Added "Edit on GitHub" links and last-updated timestamps on all pages
- Generated OpenAPI spec and auto-generated API reference pages
- Removed stale planning docs (`CUDA_BACKEND_SWAP`, `EXTERNAL_PROVIDERS`, `MLX_AUDIO`, `TTS_PROVIDER_ARCHITECTURE`, etc.)
- Sidebar groups now expand by default; root redirects to `/docs`
- Added OG image metadata and `/og` preview page
### UI & Frontend
- Added model loading status indicator and effects preset dropdown ([3187344](https://github.com/jamiepine/voicebox/commit/3187344))
- Fixed take-label race condition during regeneration
- Added accessible focus styling to select component
- Softened select focus indicator opacity
- Addressed 4 critical and 12 major issues from CodeRabbit review
### Bug Fixes ([#295](https://github.com/jamiepine/voicebox/pull/295))
- Fixed sample uploads crashing the server — audio decoding now runs in a thread pool instead of blocking the async event loop ([#278](https://github.com/jamiepine/voicebox/issues/278))
- Fixed generation list not updating when a generation completes — switched to `refetchQueries` for reliable cache busting, added SSE error fallback, and page reset on completion ([#231](https://github.com/jamiepine/voicebox/issues/231))
- Fixed error toasts showing `[object Object]` instead of the actual error message ([#290](https://github.com/jamiepine/voicebox/issues/290))
- Added Whisper model selection (`base`, `small`, `medium`, `large`, `turbo`) and expanded language support to the `/transcribe` endpoint ([#233](https://github.com/jamiepine/voicebox/issues/233))
- Upgraded CUDA backend build from cu121 to cu126 for RTX 50-series (Blackwell) GPU support ([#289](https://github.com/jamiepine/voicebox/issues/289))
- Handled client disconnects in SSE and streaming endpoints to suppress `[Errno 32] Broken Pipe` errors ([#248](https://github.com/jamiepine/voicebox/issues/248))
- Fixed Docker build failure from pip hash mismatch on Qwen3-TTS dependencies ([#286](https://github.com/jamiepine/voicebox/issues/286))
- Added 50 MB upload size limit with chunked reads to prevent unbounded memory allocation on sample uploads
- Eliminated redundant double audio decode in sample processing pipeline
### Platform Fixes
- Replaced `netstat` with `TcpStream` + PowerShell for Windows port detection ([#277](https://github.com/jamiepine/voicebox/pull/277))
- Fixed Docker frontend build and cleaned up Docker docs
- Fixed macOS download links to use `.dmg` instead of `.app.tar.gz`
- Added dynamic download redirect routes to landing site
### Release Tooling
- Added `draft-release-notes` and `release-bump` agent skills
- Wired CI release workflow to extract notes from `CHANGELOG.md` for GitHub Releases
- Backfilled changelog with all historical releases
## [0.2.3] - 2026-03-15
The "it works in dev but not in prod" release. This version fixes a series of PyInstaller bundling issues that prevented model downloading, loading, generation, and progress tracking from working in production builds.
### Model Downloads Now Actually Work
The v0.2.1/v0.2.2 builds could not download or load models that weren't already cached from a dev install. This release fixes the entire chain:
- **Chatterbox, Chatterbox Turbo, and LuxTTS** all download, load, and generate correctly in bundled builds
- **Real-time download progress** — byte-level progress bars now work in production. The root cause: `huggingface_hub` silently disables tqdm progress bars based on logger level, which prevented our progress tracker from receiving byte updates. We now force-enable the internal counter regardless.
- **Fixed Python 3.12.0 `code.replace()` bug** — the macOS build was on Python 3.12.0, which has a [known CPython bug](https://github.com/pyinstaller/pyinstaller/issues/7992) that corrupts bytecode when PyInstaller rewrites code objects. This caused `NameError: name 'obj' is not defined` crashes during scipy/torch imports. Upgraded to Python 3.12.13.
### PyInstaller Fixes
- Collect all `inflect` files — `typeguard`'s `@typechecked` decorator calls `inspect.getsource()` at import time, which needs `.py` source files, not just bytecode. Fixes LuxTTS "could not get source code" error.
- Collect all `perth` files — bundles the pretrained watermark model (`hparams.yaml`, `.pth.tar`) needed by Chatterbox at runtime
- Collect all `piper_phonemize` files — bundles `espeak-ng-data/` (phoneme tables, language dicts) needed by LuxTTS for text-to-phoneme conversion
- Set `ESPEAK_DATA_PATH` in frozen builds so the espeak-ng C library finds the bundled data instead of looking at `/usr/share/espeak-ng-data/`
- Collect all `linacodec` files — fixes `inspect.getsource` error in Vocos codec
- Collect all `zipvoice` files — fixes source code lookup in LuxTTS voice cloning
- Copy metadata for `requests`, `transformers`, `huggingface-hub`, `tokenizers`, `safetensors`, `tqdm` — fixes `importlib.metadata` lookups in frozen binary
- Add hidden imports for `chatterbox`, `chatterbox_turbo`, `luxtts`, `zipvoice` backends
- Add `multiprocessing.freeze_support()` to fix resource_tracker subprocess crash in frozen binary
- `--noconsole` now only applied on Windows — macOS/Linux need stdout/stderr for Tauri sidecar log capture
- Hardened `sys.stdout`/`sys.stderr` devnull redirect to test writability, not just `None` check
### Updater
- Fixed updater artifact generation with `v1Compatible` for `tauri-action` signature files
- Updated `tauri-action` to v0.6 to fix updater JSON and `.sig` generation
### Other Fixes
- Full traceback logging on all backend model loading errors (was just `str(e)` before)
## [0.2.2] - 2026-03-15
- Fix Chatterbox model support in bundled builds
- Fix LuxTTS/ZipVoice support in bundled builds
- Auto-update CUDA binary when app version changes
- CUDA download progress bar
- Fix server process staying alive on macOS (SIGHUP handling, watchdog grace period)
- Hide console window when running CUDA binary on Windows
## [0.2.1] - 2026-03-15
Voicebox v0.1.x was a single-engine voice cloning app built around Qwen3-TTS. v0.2.0 is a ground-up rethink: four TTS engines, 23 languages, paralinguistic emotion controls, a post-processing effects pipeline, unlimited generation length, an async generation queue, and support for every major GPU vendor. Plus Docker.
### New TTS Engines
#### Multi-Engine Architecture
Voicebox now runs **four independent TTS engines** behind a thread-safe per-engine backend registry. Switch engines per-generation from a single dropdown — no restart required.
| Engine | Languages | Size | Key Strengths |
| --------------------------- | --------- | ------- | --------------------------------------------- |
| **Qwen3-TTS 1.7B** | 10 | ~3.5 GB | Highest quality, delivery instructions |
| **Qwen3-TTS 0.6B** | 10 | ~1.2 GB | Lighter, faster variant |
| **LuxTTS** | English | ~300 MB | CPU-friendly, 48 kHz output, 150x realtime |
| **Chatterbox Multilingual** | 23 | ~3.2 GB | Broadest language coverage, zero-shot cloning |
| **Chatterbox Turbo** | English | ~1.5 GB | 350M params, low latency, paralinguistic tags |
#### Chatterbox Multilingual — 23 Languages ([#257](https://github.com/jamiepine/voicebox/pull/257))
Zero-shot voice cloning in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
#### LuxTTS — Lightweight English TTS ([#254](https://github.com/jamiepine/voicebox/pull/254))
A fast, CPU-friendly English engine. ~300 MB download, 48 kHz output, runs at 150x realtime on CPU.
#### Chatterbox Turbo — Expressive English ([#258](https://github.com/jamiepine/voicebox/pull/258))
A fast 350M-parameter English model with inline paralinguistic tags.
#### Paralinguistic Tags Autocomplete ([#265](https://github.com/jamiepine/voicebox/pull/265))
Type `/` in the text input with Chatterbox Turbo selected to open an autocomplete for **9 expressive tags**: `[laugh]` `[chuckle]` `[gasp]` `[cough]` `[sigh]` `[groan]` `[sniff]` `[shush]` `[clear throat]`
### Generation
#### Unlimited Generation Length — Auto-Chunking ([#266](https://github.com/jamiepine/voicebox/pull/266))
Long text is now automatically split at sentence boundaries, generated per-chunk, and crossfaded back together. Engine-agnostic.
- Auto-chunking limit slider — 100–5,000 chars (default 800)
- Crossfade slider — 0–200ms (default 50ms)
- Max text length raised to 50,000 characters
- Smart splitting respects abbreviations, CJK punctuation, and `[tags]`
#### Asynchronous Generation Queue ([#269](https://github.com/jamiepine/voicebox/pull/269))
Generation is now fully non-blocking. Serial execution queue prevents GPU contention. Real-time SSE status streaming.
#### Generation Versions
Every generation now supports multiple versions with provenance tracking — original, effects versions, takes, source tracking, version pinning in stories, and favorites.
### Post-Processing Effects ([#271](https://github.com/jamiepine/voicebox/pull/271))
A full audio effects system powered by Spotify's `pedalboard` library: Pitch Shift, Reverb, Delay, Chorus/Flanger, Compressor, Gain, High-Pass Filter, Low-Pass Filter. 4 built-in presets, custom presets, per-profile default effects, and live preview.
### Platform Support
- **Windows Support** ([#272](https://github.com/jamiepine/voicebox/pull/272)) — Full Windows support with CUDA GPU detection
- **Linux** ([#262](https://github.com/jamiepine/voicebox/pull/262)) — AMD ROCm, NVIDIA GBM fix, WebKitGTK mic access (build from source)
- **NVIDIA CUDA Backend Swap** ([#252](https://github.com/jamiepine/voicebox/pull/252)) — Download and swap in CUDA backend from within the app
- **Intel Arc (XPU) and DirectML** — PyTorch backend supports Intel Arc and DirectML
- **Docker + Web Deployment** ([#161](https://github.com/jamiepine/voicebox/pull/161)) — 3-stage build, non-root runtime, health checks
- **Whisper Turbo** — Added `openai/whisper-large-v3-turbo` as a transcription model option
### Model Management ([#268](https://github.com/jamiepine/voicebox/pull/268))
Per-model unload, custom models directory, model folder migration, download cancel/clear UI ([#238](https://github.com/jamiepine/voicebox/pull/238)), restructured settings UI.
### Security & Reliability
- CORS hardening ([#88](https://github.com/jamiepine/voicebox/pull/88))
- Network access toggle ([#133](https://github.com/jamiepine/voicebox/pull/133))
- Offline crash fix ([#152](https://github.com/jamiepine/voicebox/pull/152))
- Atomic audio saves ([#263](https://github.com/jamiepine/voicebox/pull/263))
- Filesystem health endpoint
- Chatterbox float64 dtype fix ([#264](https://github.com/jamiepine/voicebox/pull/264))
### Accessibility ([#243](https://github.com/jamiepine/voicebox/pull/243))
Screen reader support, keyboard navigation, state-aware `aria-label` attributes on all interactive controls.
### UI Polish
- Redesigned landing page ([#274](https://github.com/jamiepine/voicebox/pull/274))
- Voices tab overhaul with inline inspector
- Responsive layout improvements
- Duplicate profile name validation ([#175](https://github.com/jamiepine/voicebox/pull/175))
### Community Contributors
[@haosenwang1018](https://github.com/haosenwang1018), [@Balneario-de-Cofrentes](https://github.com/Balneario-de-Cofrentes), [@ageofalgo](https://github.com/ageofalgo), [@mikeswann](https://github.com/mikeswann), [@rayl15](https://github.com/rayl15), [@mpecanha](https://github.com/mpecanha), [@ways2read](https://github.com/ways2read), [@ieguiguren](https://github.com/ieguiguren), [@Vaibhavee89](https://github.com/Vaibhavee89), [@pandego](https://github.com/pandego), [@luminest-llc](https://github.com/luminest-llc)
## [0.1.13] - 2026-02-23
### Stability and reliability
- [#95](https://github.com/jamiepine/voicebox/pull/95) Fix: selecting 0.6B model still downloads and uses 1.7B
- [#93](https://github.com/jamiepine/voicebox/pull/93) fix(mlx): bundle native libs and broaden error handling for Apple Silicon
- [#79](https://github.com/jamiepine/voicebox/pull/79) fix: handle non-ASCII filenames in Content-Disposition headers
- [#78](https://github.com/jamiepine/voicebox/pull/78) fix: guard getUserMedia call against undefined mediaDevices in non-secure contexts
- [#77](https://github.com/jamiepine/voicebox/pull/77) fix: await for confirmation before deleting voices and channels
- [#128](https://github.com/jamiepine/voicebox/pull/128) fix: resolve multiple issues (#96, #119, #111, #108, #121, #125, #127)
- [#40](https://github.com/jamiepine/voicebox/pull/40) Fix: audio export path resolution
### Build and packaging
- [#122](https://github.com/jamiepine/voicebox/pull/122) fix(web): add @tailwindcss/vite plugin to web config
- [#126](https://github.com/jamiepine/voicebox/pull/126) Create requirements.txt
### UX and docs
- [#44](https://github.com/jamiepine/voicebox/pull/44) Enhances floating generate box UX
- [#57](https://github.com/jamiepine/voicebox/pull/57) chore: updates repo URL in README
- [#146](https://github.com/jamiepine/voicebox/pull/146) Add Spacebot banner to landing page
- [#1](https://github.com/jamiepine/voicebox/pull/1) Improvements
## [0.1.12] - 2026-01-31
### Model Download UX Overhaul
- Real-time download progress tracking with accurate percentage and speed info
- No more downloading notifications during generation even when its not downloading
- Better error handling and status reporting throughout the download process
### Other Improvements
- Enhanced health check endpoint with GPU type information
- Improved model caching verification
- More reliable SSE progress updates
- Actual update notifications — no need to manually check in settings anymore
## [0.1.11] - 2026-01-30
- Fixed transcriptions on MLX
- Fixed model download progress (finally)
## [0.1.10] - 2026-01-30
### Faster generation on Apple Silicon
Massive speed gains, from around 20s per generation to 2-3s. Added native MLX backend support for Apple Silicon, providing significantly faster TTS and STT generation on M-series macOS machines.
- **MLX Backend** — New backend implementation optimized for Apple Silicon using MLX framework
- **Dynamic Backend Selection** — Automatically detects platform and selects between MLX (macOS) and PyTorch (other platforms)
- Refactored TTS and STT logic into modular backend implementations
- Updated build process to include MLX-specific dependencies for macOS builds
## [0.1.9] - 2026-01-30
### Improved voice profile creation flow
- Voice create drafts: No longer lose work if you close the modal
- Fixed whisper only transcribing English or Chinese, now has support for all languages
### Improved Stories editor
- Added spacebar for play/pause
- Timeline now auto-scrolls to follow playhead during playback
- Fixed misalignment of the items with mouse when picking up
- Fixed hitbox for selecting an item
- Fixed playhead jumping forward when pressing play
### Generation box improvements
- Instruct mode no longer wipes prompt text
- Improved UI cleanliness
### Misc
- Fixed "Model downloading" toast during generation when model is already downloaded
## [0.1.8] - 2026-01-29
### Model Download Timeout Issues
Fixed critical issue where model downloads would fail with "Failed to fetch" errors on Windows. Refactored download endpoints to return immediately and continue downloads in background.
### Cross-Platform Cache Path Issues
Fixed hardcoded `~/.cache/huggingface/hub` paths that don't work on Windows. All cache paths now use `hf_constants.HF_HUB_CACHE` for proper cross-platform support.
### Windows Process Management
- Added `/shutdown` endpoint for graceful server shutdown on Windows
- Added `gpu_type` field to health check response
## [0.1.7] - 2026-01-29
- Trim and split audio clips in Story Editor
- Auto-activation of stories in Story Editor with visible playhead
- Conditional auto-play support in AudioPlayer for better user control
- Refactored audio loading across HistoryTable, SampleList, and generation forms
- Audio now only auto-plays when explicitly intended, preventing unexpected playback
## [0.1.6] - 2026-01-29
### Introducing Stories
A full voice editor for composing podcasts and generated conversations.
- **Stories Editor** — Create multi-voice narratives, podcasts, or conversations with a timeline-based editor
- Compose tracks with different voices
- Edit and arrange audio segments inline
- Build generated conversations with multiple participants
- **Improved Voice Generation UI** — Auto-resizing input, default voice selection, better layout
- **Track Editor Integration** — Inline track editing within story items
## [0.1.5] - 2026-01-28
Fixed recording length limit at 0:29 to auto stop instead of passing the limit and getting an error, which would cause users to lose their recording.
## [0.1.4] - 2026-01-28
- Audio channel management system
- Native audio playback handling in AudioPlayer component
- Refactored ConnectionForm and Checkbox components
- Improved layout consistency and responsiveness
- Added safe area constants for better responsive design
## [0.1.3] - 2026-01-27
- Improved the generate textbox
- Maybe fixed Windows autoupdate restarting entire computer
## [0.1.2] - 2026-01-27
### Audio Capture & Format Conversion
- Added audio format conversion util
- Enhanced system audio capture on macOS and Windows
- Improved audio recording hooks
- Added audio input entitlement for macOS
- Added audio capture tests
### Update System
- Enhanced auto-updater functionality and update status display
## [0.1.1] - 2026-01-27
### Platform Support
- **macOS Audio Capture** — Native audio capture support for sample creation
- **Windows Audio Capture** — WASAPI implementation with improved thread safety
- **Linux Support** — Temporarily removed builds due to runner disk space constraints
### Audio Features
- Play/pause for audio samples across all components
- Three new sample components: Recording, System capture, Upload with drag-and-drop
- Audio validation, error handling, and consistent cleanup
### Voice Profile Management
- Profile import with file size validation (100MB limit)
- Enhanced profile form with new audio sample components
- Drag-and-drop support for audio file uploads
### Server Management
- Changed default URL from `localhost:8000` to `127.0.0.1:17493`
- Server reuse logic, "keep server running" preference, orphaned process handling
### Build & Release
- Added `.bumpversion.cfg` for automated version management
- Enhanced icon generation script for multi-size Windows icons
### Bug Fixes
- Fixed date formatting for timezone-less date strings
- Fixed getLatestRelease file filtering
- Improved audio duration metadata on Windows
## [0.1.0] - 2026-01-27
The first public release of Voicebox — an open-source voice synthesis studio powered by Qwen3-TTS.
### Voice Cloning with Qwen3-TTS
- Automatic model download from HuggingFace
- Multiple model sizes (1.7B and 0.6B)
- Voice prompt caching for instant regeneration
- English and Chinese support
### Voice Profile Management
- Create profiles from audio files or record directly in the app
- Multiple samples per profile for higher quality cloning
- Import/Export profiles
- Automatic transcription via Whisper
### Speech Generation
- Simple text-to-speech with profile selection
- Seed control for reproducible generations
- Long-form support up to 5,000 characters
### Generation History
- Full history with metadata
- Search by text content
- Inline playback and download
### Flexible Deployment
- Local mode with bundled backend
- Remote mode for GPU servers on your network
- One-click server setup
### Desktop Experience
- Built with Tauri v2 (Rust) — native performance, not Electron
- Cross-platform: macOS and Windows
- No Python installation required
### Tech Stack
Tauri v2, React, TypeScript, Tailwind CSS, FastAPI, Qwen3-TTS, Whisper, SQLite
[Unreleased]: https://github.com/jamiepine/voicebox/compare/v0.4.1...HEAD
[0.4.1]: https://github.com/jamiepine/voicebox/compare/v0.4.0...v0.4.1
[0.4.0]: https://github.com/jamiepine/voicebox/compare/v0.3.0...v0.4.0
[0.3.0]: https://github.com/jamiepine/voicebox/compare/v0.2.3...v0.3.0
[0.2.3]: https://github.com/jamiepine/voicebox/compare/v0.2.2...v0.2.3
[0.2.2]: https://github.com/jamiepine/voicebox/compare/v0.2.1...v0.2.2
[0.2.1]: https://github.com/jamiepine/voicebox/compare/v0.1.13...v0.2.1
[0.1.13]: https://github.com/jamiepine/voicebox/compare/v0.1.12...v0.1.13
[0.1.12]: https://github.com/jamiepine/voicebox/compare/v0.1.11...v0.1.12
[0.1.11]: https://github.com/jamiepine/voicebox/compare/v0.1.10...v0.1.11
[0.1.10]: https://github.com/jamiepine/voicebox/compare/v0.1.9...v0.1.10
[0.1.9]: https://github.com/jamiepine/voicebox/compare/v0.1.8...v0.1.9
[0.1.8]: https://github.com/jamiepine/voicebox/compare/v0.1.7...v0.1.8
[0.1.7]: https://github.com/jamiepine/voicebox/compare/v0.1.6...v0.1.7
[0.1.6]: https://github.com/jamiepine/voicebox/compare/v0.1.5...v0.1.6
[0.1.5]: https://github.com/jamiepine/voicebox/compare/v0.1.4...v0.1.5
[0.1.4]: https://github.com/jamiepine/voicebox/compare/v0.1.3...v0.1.4
[0.1.3]: https://github.com/jamiepine/voicebox/compare/v0.1.2...v0.1.3
[0.1.2]: https://github.com/jamiepine/voicebox/compare/v0.1.1...v0.1.2
[0.1.1]: https://github.com/jamiepine/voicebox/compare/v0.1.0...v0.1.1
[0.1.0]: https://github.com/jamiepine/voicebox/releases/tag/v0.1.0
+50 -91
View File
@@ -27,87 +27,47 @@ Thank you for your interest in contributing to Voicebox! This document provides
```bash
rustc --version # Check if installed
```
- **[Tauri Prerequisites](https://v2.tauri.app/start/prerequisites)** - Tauri-specific system dependencies (varies by OS).
- **Git** - Version control
### Development Setup
**Using the Makefile (recommended for macOS/Linux):** Run `make setup` to install all dependencies, then `make dev` to start development servers. See `make help` for all available commands.
Install [just](https://github.com/casey/just) (`brew install just`, `cargo install just`, or `winget install Casey.Just`), then:
**Manual setup (required for Windows):**
```bash
git clone https://github.com/YOUR_USERNAME/voicebox.git
cd voicebox
1. **Fork and clone the repository**
```bash
git clone https://github.com/YOUR_USERNAME/voicebox.git
cd voicebox
```
just setup # creates venv, installs Python + JS deps
just dev # starts backend + desktop app
```
2. **Install JavaScript dependencies**
```bash
bun install
```
This installs dependencies for:
- `app/` - Shared React frontend
- `tauri/` - Tauri desktop wrapper
- `web/` - Web deployment wrapper
`just setup` handles everything automatically, including:
- Creating a Python virtual environment
- Installing Python dependencies (with CUDA PyTorch on Windows if an NVIDIA GPU is detected)
- Installing MLX dependencies on Apple Silicon
- Installing JavaScript dependencies
3. **Set up Python backend**
```bash
cd backend
# Create virtual environment
python -m venv venv
# Activate virtual environment
source venv/bin/activate # On macOS/Linux
# or
venv\Scripts\activate # On Windows
# Install Python dependencies
pip install -r requirements.txt
# Install MLX dependencies (Apple Silicon only - for faster inference)
# On Apple Silicon, this enables native Metal acceleration
if [[ $(uname -m) == "arm64" ]]; then
pip install -r requirements-mlx.txt
fi
# Install Qwen3-TTS (required for voice synthesis)
pip install git+https://github.com/QwenLM/Qwen3-TTS.git
```
`just dev` starts the backend and desktop app together. If a backend is already running (e.g. from `just dev-backend` in another terminal), it detects it and only starts the frontend.
4. **Start development servers**
Other useful commands:
Development requires two terminals: one for the Python backend, one for the Tauri app.
```bash
just dev-web # backend + web app (no Tauri/Rust build)
just dev-backend # backend only
just dev-frontend # Tauri app only (backend must be running)
just kill # stop all dev processes
just clean-all # nuke everything and start fresh
just --list # see all available commands
```
**Terminal 1: Backend server** (start this first)
```bash
cd backend
source venv/bin/activate # Activate venv if not already active
bun run dev:server
# Or manually: uvicorn main:app --reload --port 17493
```
Backend will be available at `http://localhost:17493`
> **Note:** In dev mode, the app connects to a manually-started Python server.
> The bundled server binary is only used in production builds.
**Terminal 2: Desktop app**
```bash
bun run dev
```
This will:
- Create a placeholder sidecar binary (for Tauri compilation)
- Start Vite dev server on port 5173
- Launch Tauri window pointing to localhost:5173
- Connect to the Python server you started in Terminal 1
- Enable hot reload
#### Windows Notes
> **Note:** In dev mode, the app connects to your manually-started Python server.
> The bundled server binary is only used in production builds.
**Optional: Web app**
```bash
bun run dev:web
```
Web app will be available at `http://localhost:5174`
The justfile works natively on Windows via PowerShell. No WSL or Git Bash required. On Windows with an NVIDIA GPU, `just setup` automatically installs CUDA-enabled PyTorch for GPU acceleration.
### Model Downloads
@@ -119,25 +79,30 @@ First-time usage will be slower due to model downloads, but subsequent runs will
### Building
**Build everything (recommended):**
**Build production app:**
```bash
bun run build
just build # Build CPU server binary + Tauri installer
```
This automatically:
1. Builds the Python server binary (`./scripts/build-server.sh`)
2. Builds the Tauri desktop app (`cd tauri && bun run tauri build`)
On Windows, to build with CUDA support for local testing:
```bash
just build-local # Build CPU + CUDA server binaries + Tauri installer
```
This builds the CPU sidecar (bundled with the app), the CUDA binary (placed in `%APPDATA%/com.voicebox.app/backends/` for runtime GPU switching), and the installable Tauri app.
Creates platform-specific installers (`.dmg`, `.msi`, `.AppImage`) in `tauri/src-tauri/target/release/bundle/`.
**Note:** The build process detects your platform and includes the appropriate backend (MLX for Apple Silicon, PyTorch for others).
**Individual build targets:**
**Build server binary only:**
```bash
bun run build:server
# or
./scripts/build-server.sh
just build-server # CPU server binary only
just build-server-cuda # CUDA server binary only (Windows)
just build-tauri # Tauri desktop app only
just build-web # Web app only
```
Creates platform-specific binary in `tauri/src-tauri/binaries/`
**Building with local Qwen3-TTS development version:**
@@ -145,17 +110,10 @@ If you're actively developing or modifying the Qwen3-TTS library, set the `QWEN_
```bash
export QWEN_TTS_PATH=~/path/to/your/Qwen3-TTS
bun run build:server
just build-server
```
This makes PyInstaller use your local qwen-tts version instead of the pip-installed package. Useful when testing changes to the TTS library before they're published to PyPI or when using an editable install (`pip install -e`).
**Build web app:**
```bash
cd web
bun run build
```
Output in `web/dist/`
This makes PyInstaller use your local qwen-tts version instead of the pip-installed package.
### Generate OpenAPI Client
@@ -302,7 +260,7 @@ voicebox/
### ✨ New Features
- Check the roadmap in README.md
- Check the roadmap in README.md and the engineering status in [`docs/PROJECT_STATUS.md`](docs/PROJECT_STATUS.md) before proposing work — it lists prioritized tasks (Tier 1 → 3), known architectural bottlenecks, and candidate TTS engines already under evaluation (including why some have been backlogged)
- Discuss major features in an issue first
- Keep features focused and well-scoped
@@ -401,25 +359,26 @@ Releases are managed by maintainers:
## Troubleshooting
See [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md) for common issues and solutions.
See [docs/content/docs/overview/troubleshooting.mdx](docs/content/docs/overview/troubleshooting.mdx) for common issues and solutions.
**Quick fixes:**
- **Backend won't start:** Check Python version (3.11+), ensure venv is activated, install dependencies
- **Tauri build fails:** Ensure Rust is installed, clean build with `cd tauri/src-tauri && cargo clean`
- **OpenAPI client generation fails:** Ensure backend is running, check `curl http://localhost:8000/openapi.json`
- **OpenAPI client generation fails:** Ensure backend is running, check `curl http://localhost:17493/openapi.json`
## Questions?
- Open an issue for bugs or feature requests
- Check existing issues and discussions
- Review the codebase to understand patterns
- See [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md) for common issues
- See [docs/content/docs/overview/troubleshooting.mdx](docs/content/docs/overview/troubleshooting.mdx) for common issues
## Additional Resources
- [README.md](README.md) - Project overview
- [backend/README.md](backend/README.md) - API documentation
- [docs/PROJECT_STATUS.md](docs/PROJECT_STATUS.md) - Living engineering roadmap: architecture, shipped vs in-flight work, prioritized open issues, candidate TTS engines under evaluation, architectural bottlenecks. Keep this updated when you ship significant features, close or backlog a model integration, or identify new bottlenecks.
- [docs/AUTOUPDATER_QUICKSTART.md](docs/AUTOUPDATER_QUICKSTART.md) - Auto-updater setup
- [SECURITY.md](SECURITY.md) - Security policy
- [CHANGELOG.md](CHANGELOG.md) - Version history
+83
View File
@@ -0,0 +1,83 @@
# ============================================================
# Voicebox — Local TTS Server with Web UI (CPU)
# 3-stage build: Frontend → Python deps → Runtime
# ============================================================
# === Stage 1: Build frontend ===
FROM oven/bun:1 AS frontend
WORKDIR /build
# Copy workspace config and frontend source
COPY package.json bun.lock CHANGELOG.md ./
COPY app/ ./app/
COPY web/ ./web/
# Strip workspaces not needed for web build, and fix trailing comma
RUN sed -i '/"tauri"/d; /"landing"/d' package.json && \
sed -i -z 's/,\n ]/\n ]/' package.json
RUN bun install --no-save
# Build frontend (skip tsc — upstream has pre-existing type errors)
RUN cd web && bunx --bun vite build
# === Stage 2: Build Python dependencies ===
FROM python:3.11-slim AS backend-builder
WORKDIR /build
RUN apt-get update && apt-get install -y --no-install-recommends \
git \
build-essential \
&& rm -rf /var/lib/apt/lists/*
RUN pip install --no-cache-dir --upgrade pip
COPY backend/requirements.txt .
RUN pip install --no-cache-dir --prefix=/install -r requirements.txt
RUN pip install --no-cache-dir --prefix=/install --no-deps chatterbox-tts
RUN pip install --no-cache-dir --prefix=/install --no-deps hume-tada
RUN pip install --no-cache-dir --prefix=/install \
git+https://github.com/QwenLM/Qwen3-TTS.git
# === Stage 3: Runtime ===
FROM python:3.11-slim
# Create non-root user for security
RUN groupadd -r voicebox && \
useradd -r -g voicebox -m -s /bin/bash voicebox
WORKDIR /app
# Install only runtime system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
ffmpeg \
curl \
&& rm -rf /var/lib/apt/lists/*
# Copy installed Python packages from builder stage
COPY --from=backend-builder /install /usr/local
# Copy backend application code
COPY --chown=voicebox:voicebox backend/ /app/backend/
# Copy built frontend from frontend stage
COPY --from=frontend --chown=voicebox:voicebox /build/web/dist /app/frontend/
# Create data directories owned by non-root user
RUN mkdir -p /app/data/generations /app/data/profiles /app/data/cache \
&& chown -R voicebox:voicebox /app/data
# Switch to non-root user
USER voicebox
# Expose the API port
EXPOSE 17493
# Health check — auto-restart if the server hangs
HEALTHCHECK --interval=30s --timeout=10s --retries=3 --start-period=60s \
CMD curl -f http://localhost:17493/health || exit 1
# Start the FastAPI server
CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "17493"]
-245
View File
@@ -1,245 +0,0 @@
# Voicebox Makefile
# Unix-only (macOS/Linux). Windows users should use WSL.
SHELL := /bin/bash
.DEFAULT_GOAL := help
# Directories
BACKEND_DIR := backend
TAURI_DIR := tauri
WEB_DIR := web
APP_DIR := app
# Python (prefer 3.12, fallback to 3.13, then python3)
PYTHON := $(shell command -v python3.12 2>/dev/null || command -v python3.13 2>/dev/null || echo python3)
VENV := $(CURDIR)/$(BACKEND_DIR)/venv
VENV_BIN := $(VENV)/bin
PIP := $(VENV_BIN)/pip
PYTHON_VENV := $(VENV_BIN)/python
# Colors for output
BLUE := \033[0;34m
GREEN := \033[0;32m
YELLOW := \033[0;33m
NC := \033[0m # No Color
.PHONY: help
help: ## Show this help message
@echo -e "$(BLUE)Voicebox$(NC) - Development Commands"
@echo ""
@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | \
awk 'BEGIN {FS = ":.*?## "}; {printf " $(GREEN)%-20s$(NC) %s\n", $$1, $$2}'
# =============================================================================
# SETUP
# =============================================================================
.PHONY: setup setup-js setup-python setup-rust
setup: setup-js setup-python ## Full project setup (all dependencies)
@echo -e "$(GREEN)✓ Setup complete!$(NC)"
@echo -e " Run $(YELLOW)make dev$(NC) to start development servers"
setup-js: ## Install JavaScript dependencies (bun)
@echo -e "$(BLUE)Installing JavaScript dependencies...$(NC)"
bun install
setup-python: $(VENV)/bin/activate ## Set up Python virtual environment and dependencies
@echo -e "$(BLUE)Installing Python dependencies...$(NC)"
$(PIP) install --upgrade pip
$(PIP) install -r $(BACKEND_DIR)/requirements.txt
@if [ "$$(uname -m)" = "arm64" ] && [ "$$(uname)" = "Darwin" ]; then \
echo -e "$(BLUE)Detected Apple Silicon - installing MLX dependencies...$(NC)"; \
$(PIP) install -r $(BACKEND_DIR)/requirements-mlx.txt; \
echo -e "$(GREEN)✓ MLX backend enabled (native Metal acceleration)$(NC)"; \
fi
$(PIP) install git+https://github.com/QwenLM/Qwen3-TTS.git
@echo -e "$(GREEN)✓ Python environment ready$(NC)"
$(VENV)/bin/activate:
@echo -e "$(BLUE)Creating Python virtual environment...$(NC)"
@PY_MINOR=$$($(PYTHON) -c "import sys; print(sys.version_info[1])"); \
if [ "$$PY_MINOR" -gt 13 ]; then \
echo -e "$(YELLOW)Warning: Python 3.$$PY_MINOR detected. ML packages may not be compatible.$(NC)"; \
echo -e "$(YELLOW)Recommended: Use Python 3.12 or 3.13 (brew install [email protected])$(NC)"; \
fi
$(PYTHON) -m venv $(VENV)
setup-rust: ## Install Rust toolchain (if not present)
@command -v rustc >/dev/null 2>&1 || curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
# =============================================================================
# DEVELOPMENT
# =============================================================================
.PHONY: dev dev-backend dev-frontend dev-web kill-dev
dev: ## Start backend + desktop app (parallel)
@echo -e "$(BLUE)Starting development servers...$(NC)"
@echo -e "$(YELLOW)Note: If Tauri fails, run 'make build-server' first or use separate terminals$(NC)"
@trap 'kill 0' EXIT; \
$(MAKE) dev-backend & \
sleep 2 && $(MAKE) dev-frontend & \
wait
dev-backend: ## Start FastAPI backend server
@echo -e "$(BLUE)Starting backend server on http://localhost:17493$(NC)"
$(VENV_BIN)/uvicorn backend.main:app --reload --port 17493
dev-frontend: ## Start Tauri desktop app
@echo -e "$(BLUE)Starting Tauri desktop app...$(NC)"
bun run dev
dev-web: ## Start backend + web app (parallel)
@echo -e "$(BLUE)Starting web development servers...$(NC)"
@trap 'kill 0' EXIT; \
$(MAKE) dev-backend & \
sleep 2 && cd $(WEB_DIR) && bun run dev & \
wait
kill-dev: ## Kill all development processes
@echo -e "$(YELLOW)Killing development processes...$(NC)"
-pkill -f "uvicorn main:app" 2>/dev/null || true
-pkill -f "vite" 2>/dev/null || true
@echo -e "$(GREEN)✓ Processes killed$(NC)"
# =============================================================================
# BUILD
# =============================================================================
.PHONY: build build-server build-tauri build-web
build: build-server build-tauri ## Build everything (server binary + desktop app)
@echo -e "$(GREEN)✓ Build complete!$(NC)"
build-server: ## Build Python server binary
@echo -e "$(BLUE)Building server binary...$(NC)"
PATH="$(VENV_BIN):$$PATH" ./scripts/build-server.sh
build-tauri: ## Build Tauri desktop app
@echo -e "$(BLUE)Building Tauri desktop app...$(NC)"
cd $(TAURI_DIR) && bun run tauri build
build-web: ## Build web app
@echo -e "$(BLUE)Building web app...$(NC)"
cd $(WEB_DIR) && bun run build
@echo -e "$(GREEN)✓ Web build output in $(WEB_DIR)/dist/$(NC)"
# =============================================================================
# DATABASE & API
# =============================================================================
.PHONY: db-init db-reset generate-api
db-init: $(VENV)/bin/activate ## Initialize SQLite database
@echo -e "$(BLUE)Initializing database...$(NC)"
cd $(BACKEND_DIR) && $(PYTHON_VENV) -c "from database import init_db; init_db()"
@echo -e "$(GREEN)✓ Database created at $(BACKEND_DIR)/data/voicebox.db$(NC)"
db-reset: ## Reset database (delete and reinitialize)
@echo -e "$(YELLOW)Resetting database...$(NC)"
rm -f $(BACKEND_DIR)/data/voicebox.db
$(MAKE) db-init
generate-api: ## Generate TypeScript API client from OpenAPI schema
@echo -e "$(BLUE)Generating API client...$(NC)"
@echo -e "$(YELLOW)Note: Backend must be running (make dev-backend)$(NC)"
./scripts/generate-api.sh
@echo -e "$(GREEN)✓ API client generated in $(APP_DIR)/src/lib/api/$(NC)"
# =============================================================================
# CODE QUALITY
# =============================================================================
.PHONY: lint format typecheck check
lint: ## Run linter (Biome)
@echo -e "$(BLUE)Linting...$(NC)"
bun run lint
format: ## Format code (Biome)
@echo -e "$(BLUE)Formatting...$(NC)"
bun run format
typecheck: ## Run TypeScript type checking
@echo -e "$(BLUE)Type checking...$(NC)"
bun run tsc --noEmit
check: ## Run all checks (Biome lint + format + type check)
@echo -e "$(BLUE)Running all checks...$(NC)"
bun run check
@echo -e "$(GREEN)✓ All checks passed$(NC)"
# =============================================================================
# TESTING
# =============================================================================
.PHONY: test test-backend test-frontend
test: test-backend test-frontend ## Run all tests
@echo -e "$(GREEN)✓ All tests passed$(NC)"
test-backend: ## Run Python backend tests (requires pytest)
@echo -e "$(BLUE)Running backend tests...$(NC)"
@if [ -f "$(VENV_BIN)/pytest" ]; then \
cd $(BACKEND_DIR) && $(VENV_BIN)/pytest -v; \
else \
echo -e "$(YELLOW)pytest not installed. Run: $(PIP) install pytest$(NC)"; \
exit 1; \
fi
test-frontend: ## Run frontend tests (requires test script in package.json)
@echo -e "$(BLUE)Running frontend tests...$(NC)"
@if bun run test --help >/dev/null 2>&1; then \
bun run test; \
else \
echo -e "$(YELLOW)No test script configured$(NC)"; \
exit 1; \
fi
# =============================================================================
# LOGS & DEBUGGING
# =============================================================================
.PHONY: logs docs
logs: ## Tail backend logs
@echo -e "$(BLUE)Tailing logs (Ctrl+C to stop)...$(NC)"
tail -f $(BACKEND_DIR)/logs/*.log 2>/dev/null || echo "No log files found"
docs: ## Open API documentation (backend must be running)
@echo -e "$(BLUE)Opening API docs...$(NC)"
open http://localhost:17493/docs 2>/dev/null || xdg-open http://localhost:17493/docs
# =============================================================================
# CLEAN
# =============================================================================
.PHONY: clean clean-python clean-build clean-all
clean: ## Clean build artifacts
@echo -e "$(BLUE)Cleaning build artifacts...$(NC)"
rm -rf $(TAURI_DIR)/src-tauri/target/release
rm -rf $(WEB_DIR)/dist
rm -rf $(APP_DIR)/dist
@echo -e "$(GREEN)✓ Build artifacts cleaned$(NC)"
clean-python: ## Clean Python cache and virtual environment
@echo -e "$(BLUE)Cleaning Python files...$(NC)"
rm -rf $(VENV)
find $(BACKEND_DIR) -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
find $(BACKEND_DIR) -type f -name "*.pyc" -delete 2>/dev/null || true
@echo -e "$(GREEN)✓ Python environment cleaned$(NC)"
clean-build: ## Clean Rust/Tauri build cache
@echo -e "$(BLUE)Cleaning Rust build cache...$(NC)"
cd $(TAURI_DIR)/src-tauri && cargo clean
@echo -e "$(GREEN)✓ Rust cache cleaned$(NC)"
clean-all: clean clean-python clean-build ## Nuclear clean (everything)
@echo -e "$(BLUE)Cleaning node_modules...$(NC)"
rm -rf node_modules
rm -rf $(APP_DIR)/node_modules
rm -rf $(TAURI_DIR)/node_modules
rm -rf $(WEB_DIR)/node_modules
@echo -e "$(GREEN)✓ Full clean complete$(NC)"
+161 -128
View File
@@ -6,7 +6,7 @@
<p align="center">
<strong>The open-source voice synthesis studio.</strong><br/>
Clone voices. Generate speech. Build voice-powered apps.<br/>
Clone voices. Generate speech. Apply effects. Build voice-powered apps.<br/>
All running locally on your machine.
</p>
@@ -23,14 +23,18 @@
<a href="https://github.com/jamiepine/voicebox/blob/main/LICENSE">
<img src="https://img.shields.io/github/license/jamiepine/voicebox?style=flat" alt="License" />
</a>
<a href="https://deepwiki.com/jamiepine/voicebox">
<img src="https://img.shields.io/static/v1?label=Ask&message=DeepWiki&color=5B6EF7" alt="Ask DeepWiki" />
</a>
</p>
<p align="center">
<a href="https://voicebox.sh">voicebox.sh</a> •
<a href="https://docs.voicebox.sh">Docs</a> •
<a href="#download">Download</a> •
<a href="#features">Features</a> •
<a href="#api">API</a> •
<a href="#roadmap">Roadmap</a>
<a href="docs/content/docs/overview/troubleshooting.mdx">Troubleshooting</a>
</p>
<br/>
@@ -59,165 +63,208 @@
## What is Voicebox?
Voicebox is a **local-first voice cloning studio** with DAW-like features for professional voice synthesis. Think of it as the **Ollama for voice** — download models, clone voices, and generate speech entirely on your machine.
Unlike cloud services that lock your voice data behind subscriptions, Voicebox gives you:
Voicebox is a **local-first voice cloning studio** — a free and open-source alternative to ElevenLabs. Clone voices from a few seconds of audio or pick from 50+ preset voices, generate speech in 23 languages across 7 TTS engines, apply post-processing effects, and compose multi-voice projects with a timeline editor.
- **Complete privacy** — models and voice data stay on your machine
- **Professional tools** — multi-track timeline editor, audio trimming, conversation mixing
- **Model flexibility** — currently powered by Qwen3-TTS, with support for XTTS, Bark, and other models coming soon
- **API-first** — use the desktop app or integrate voice synthesis into your own projects
- **7 TTS engines** — Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA, and Kokoro
- **Cloning and preset voices** — zero-shot cloning from a reference sample, or curated preset voices via Kokoro (50 voices) and Qwen CustomVoice (9 voices)
- **23 languages** — from English to Arabic, Japanese, Hindi, Swahili, and more
- **Post-processing effects** — pitch shift, reverb, delay, chorus, compression, and filters
- **Expressive speech** — paralinguistic tags like `[laugh]`, `[sigh]`, `[gasp]` via Chatterbox Turbo; natural-language delivery control via Qwen CustomVoice
- **Unlimited length** — auto-chunking with crossfade for scripts, articles, and chapters
- **Stories editor** — multi-track timeline for conversations, podcasts, and narratives
- **API-first** — REST API for integrating voice synthesis into your own projects
- **Native performance** — built with Tauri (Rust), not Electron
- **Super fast on Mac** — MLX backend with native Metal acceleration for 4-5x faster inference on Apple Silicon
Download a voice model, clone any voice from a few seconds of audio, and compose multi-voice projects with studio-grade editing tools. No Python install required, no cloud dependency, no limits.
- **Runs everywhere** — macOS (MLX/Metal), Windows (CUDA), Linux, AMD ROCm, Intel Arc, Docker
---
## Download
Voicebox is available now for macOS and Windows.
| Platform | Download |
| --------------------- | ------------------------------------------------------ |
| macOS (Apple Silicon) | [Download DMG](https://voicebox.sh/download/mac-arm) |
| macOS (Intel) | [Download DMG](https://voicebox.sh/download/mac-intel) |
| Windows | [Download MSI](https://voicebox.sh/download/windows) |
| Docker | `docker compose up` |
| Platform | Download |
|----------|----------|
| macOS (Apple Silicon) | [voicebox_aarch64.app.tar.gz](https://github.com/jamiepine/voicebox/releases/download/v0.1.0/voicebox_aarch64.app.tar.gz) |
| macOS (Intel) | [voicebox_x64.app.tar.gz](https://github.com/jamiepine/voicebox/releases/download/v0.1.0/voicebox_x64.app.tar.gz) |
| Windows (MSI) | [voicebox_0.1.0_x64_en-US.msi](https://github.com/jamiepine/voicebox/releases/download/v0.1.0/voicebox_0.1.0_x64_en-US.msi) |
| Windows (Setup) | [voicebox_0.1.0_x64-setup.exe](https://github.com/jamiepine/voicebox/releases/download/v0.1.0/voicebox_0.1.0_x64-setup.exe) |
> **[View all binaries →](https://github.com/jamiepine/voicebox/releases/latest)**
> **Linux builds coming soon** — Currently blocked by GitHub runner disk space limitations.
> **Linux** — Pre-built binaries are not yet available. See [voicebox.sh/linux-install](https://voicebox.sh/linux-install) for build-from-source instructions.
> **Having trouble?** See the [Troubleshooting Guide](docs/content/docs/overview/troubleshooting.mdx) for common install, generation, model-download, and GPU issues.
---
## Features
### Voice Cloning with Qwen3-TTS
### Multi-Engine Voice Cloning
Powered by Alibaba's **Qwen3-TTS** — a breakthrough model that achieves near-perfect voice cloning from just a few seconds of audio.
Seven TTS engines with different strengths, switchable per-generation:
- **Instant cloning** — Upload a sample, get a voice profile
- **High fidelity** — Natural prosody, emotion, and cadence
- **Multi-language** — English, Chinese, and more coming
- **Lightning fast on Mac** — MLX backend leverages Apple Silicon's Neural Engine for super fast generation
| Engine | Languages | Strengths |
| --------------------------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| **Qwen3-TTS** (0.6B / 1.7B) | 10 | High-quality multilingual cloning, delivery instructions ("speak slowly", "whisper") |
| **Qwen CustomVoice** | 10 | 9 curated preset voices with natural-language delivery control — no reference audio required |
| **LuxTTS** | English | Lightweight (~1GB VRAM), 48kHz output, 150x realtime on CPU |
| **Chatterbox Multilingual** | 23 | Broadest language coverage — Arabic, Danish, Finnish, Greek, Hebrew, Hindi, Malay, Norwegian, Polish, Swahili, Swedish, Turkish and more |
| **Chatterbox Turbo** | English | Fast 350M model with paralinguistic emotion/sound tags |
| **TADA** (1B / 3B) | 10 | HumeAI speech-language model — 700s+ coherent audio, text-acoustic dual alignment |
| **Kokoro** | 8 | 50 curated preset voices, tiny 82M model, fast CPU inference |
### Emotions & Paralinguistic Tags
Only **Chatterbox Turbo** interprets paralinguistic tags like `[laugh]` and
`[sigh]`. Qwen3-TTS, LuxTTS, Chatterbox Multilingual, and HumeAI TADA read them
literally as text.
With **Chatterbox Turbo** selected, type `/` in the text input to open the tag
inserter and add expressive tags inline with speech:
`[laugh]` `[chuckle]` `[gasp]` `[cough]` `[sigh]` `[groan]` `[sniff]` `[shush]` `[clear throat]`
### Post-Processing Effects
8 audio effects powered by Spotify's `pedalboard` library. Apply after generation, preview in real time, build reusable presets.
| Effect | Description |
| ---------------- | --------------------------------------------- |
| Pitch Shift | Up or down by up to 12 semitones |
| Reverb | Configurable room size, damping, wet/dry mix |
| Delay | Echo with adjustable time, feedback, and mix |
| Chorus / Flanger | Modulated delay for metallic or lush textures |
| Compressor | Dynamic range compression |
| Gain | Volume adjustment (-40 to +40 dB) |
| High-Pass Filter | Remove low frequencies |
| Low-Pass Filter | Remove high frequencies |
Ships with 4 built-in presets (Robotic, Radio, Echo Chamber, Deep Voice) and supports custom presets. Effects can be assigned per-profile as defaults.
### Unlimited Generation Length
Text is automatically split at sentence boundaries and each chunk is generated independently, then crossfaded together. Works with all engines.
- Configurable auto-chunking limit (100–5,000 chars)
- Crossfade slider (0–200ms) for smooth transitions
- Max text length: 50,000 characters
- Smart splitting respects abbreviations, CJK punctuation, and `[tags]`
### Generation Versions
Every generation supports multiple versions with provenance tracking:
- **Original** — clean TTS output, always preserved
- **Effects versions** — apply different effects chains from any source version
- **Takes** — regenerate with a new seed for variation
- **Source tracking** — each version records its lineage
- **Favorites** — star generations for quick access
### Async Generation Queue
Generation is non-blocking. Submit and immediately start typing the next one.
- Serial execution queue prevents GPU contention
- Real-time SSE status streaming
- Failed generations can be retried
- Stale generations from crashes auto-recover on startup
### Voice Profile Management
- **Create profiles** from audio files or record directly in-app
- **Import/Export** profiles to share or backup
- **Multi-sample support** — combine multiple samples for higher quality cloning
- **Organize** with descriptions and language tags
### Speech Generation
- **Text-to-speech** with any cloned voice
- **Batch generation** for long-form content
- **Smart caching** — regenerate instantly with voice prompt caching
- Create profiles from audio files or record directly in-app
- Import/export profiles to share or back up
- Multi-sample support for higher quality cloning
- Per-profile default effects chains
- Organize with descriptions and language tags
### Stories Editor
Create multi-voice narratives, podcasts, and conversations with a timeline-based editor.
Multi-voice timeline editor for conversations, podcasts, and narratives.
- **Multi-track composition** — arrange multiple voice tracks in a single project
- **Inline audio editing** — trim and split clips directly in the timeline
- **Auto-playback** — preview stories with synchronized playhead
- **Voice mixing** — build conversations with multiple participants
- Multi-track composition with drag-and-drop
- Inline audio trimming and splitting
- Auto-playback with synchronized playhead
- Version pinning per track clip
### Recording & Transcription
- **In-app recording** with waveform visualization
- **System audio capture** — record desktop audio on macOS and Windows
- **Automatic transcription** powered by Whisper
- **Export recordings** in multiple formats
- In-app recording with waveform visualization
- System audio capture (macOS and Windows)
- Automatic transcription powered by Whisper (including Whisper Turbo)
- Export recordings in multiple formats
### Generation History
### Model Management
- **Full history** of all generated audio
- **Search & filter** by voice, text, or date
- **Re-generate** any past generation with one click
- Per-model unload to free GPU memory without deleting downloads
- Custom models directory via `VOICEBOX_MODELS_DIR`
- Model folder migration with progress tracking
- Download cancel/clear UI
### Flexible Deployment
### GPU Support
- **Local mode** — Everything runs on your machine
- **Remote mode** — Connect to a GPU server on your network
- **One-click server** — Turn any machine into a Voicebox server
| Platform | Backend | Notes |
| ------------------------ | -------------- | ---------------------------------------------- |
| macOS (Apple Silicon) | MLX (Metal) | 4-5x faster via Neural Engine |
| Windows / Linux (NVIDIA) | PyTorch (CUDA) | Auto-downloads CUDA binary from within the app |
| Linux (AMD) | PyTorch (ROCm) | Auto-configures HSA_OVERRIDE_GFX_VERSION |
| Windows (any GPU) | DirectML | Universal Windows GPU support |
| Intel Arc | IPEX/XPU | Intel discrete GPU acceleration |
| Any | CPU | Works everywhere, just slower |
---
## API
Voicebox exposes a full REST API, so you can integrate voice synthesis into your own apps.
Voicebox exposes a full REST API for integrating voice synthesis into your own apps.
```bash
# Generate speech
curl -X POST http://localhost:8000/generate \
curl -X POST http://localhost:17493/generate \
-H "Content-Type: application/json" \
-d '{"text": "Hello world", "profile_id": "abc123", "language": "en"}'
# List voice profiles
curl http://localhost:8000/profiles
curl http://localhost:17493/profiles
# Create a profile
curl -X POST http://localhost:8000/profiles \
curl -X POST http://localhost:17493/profiles \
-H "Content-Type: application/json" \
-d '{"name": "My Voice", "language": "en"}'
```
**Use cases:**
**Use cases:** game dialogue, podcast production, accessibility tools, voice assistants, content automation.
- Game dialogue systems
- Podcast/video production pipelines
- Accessibility tools
- Voice assistants
- Content creation automation
Full API documentation available at `http://localhost:8000/docs` when running.
Full API documentation available at `http://localhost:17493/docs`.
---
## Tech Stack
| Layer | Technology |
|-------|------------|
| Desktop App | Tauri (Rust) |
| Frontend | React, TypeScript, Tailwind CSS |
| State | Zustand, React Query |
| Backend | FastAPI (Python) |
| Voice Model | Qwen3-TTS (PyTorch or MLX) |
| Transcription | Whisper (PyTorch or MLX) |
| Inference Engine | MLX (Apple Silicon) / PyTorch (Windows/Linux/Intel) |
| Database | SQLite |
| Audio | WaveSurfer.js, librosa |
**Why this stack?**
- **Tauri over Electron** — 10x smaller bundle, native performance, lower memory
- **FastAPI** — Async Python with automatic OpenAPI schema generation
- **Type-safe end-to-end** — Generated TypeScript client from OpenAPI spec
| Layer | Technology |
| ------------- | ------------------------------------------------- |
| Desktop App | Tauri (Rust) |
| Frontend | React, TypeScript, Tailwind CSS |
| State | Zustand, React Query |
| Backend | FastAPI (Python) |
| TTS Engines | Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox, Chatterbox Turbo, TADA, Kokoro |
| Effects | Pedalboard (Spotify) |
| Transcription | Whisper / Whisper Turbo (PyTorch or MLX) |
| Inference | MLX (Apple Silicon) / PyTorch (CUDA/ROCm/XPU/CPU) |
| Database | SQLite |
| Audio | WaveSurfer.js, librosa |
---
## Roadmap
Voicebox is the beginning of something bigger. Here's what's coming:
| Feature | Description |
| ----------------------- | ---------------------------------------------- |
| **Real-time Streaming** | Stream audio as it generates, word by word |
| **Voice Design** | Create new voices from text descriptions |
| **More Models** | XTTS, Bark, and other open-source voice models |
| **Plugin Architecture** | Extend with custom models and effects |
| **Mobile Companion** | Control Voicebox from your phone |
### Coming Soon
| Feature | Description |
|---------|-------------|
| **Real-time Synthesis** | Stream audio as it generates, word by word |
| **Conversation Mode** | Multi-speaker dialogues with automatic turn-taking |
| **Voice Effects** | Pitch shift, reverb, M3GAN-style effects |
| **Timeline Editor** | Audio studio with word-level precision editing |
| **More Models** | XTTS, Bark, and other open-source voice models |
### Future Vision
- **Voice Design** — Create new voices from text descriptions
- **Project System** — Save and load complex multi-voice sessions
- **Plugin Architecture** — Extend with custom models and effects
- **Mobile Companion** — Control Voicebox from your phone
Voicebox aims to be the **one-stop shop for everything voice** — cloning, synthesis, editing, effects, and beyond.
For the **full engineering status, open-issue triage, and prioritized work queue**, see [`docs/PROJECT_STATUS.md`](docs/PROJECT_STATUS.md) — a living document that tracks what's shipped, what's in-flight, candidate TTS engines under evaluation, and why we've accepted or backlogged specific integrations.
---
@@ -225,46 +272,32 @@ Voicebox aims to be the **one-stop shop for everything voice** — cloning, synt
See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed setup and contribution guidelines.
**Using the Makefile (recommended):** Run `make help` to see all available commands for setup, development, building, and testing.
### Quick Start
**With Makefile (Unix/macOS/Linux):**
```bash
# Clone the repo
git clone https://github.com/voicebox-sh/voicebox.git
git clone https://github.com/jamiepine/voicebox.git
cd voicebox
# Setup everything
make setup
# Start development
make dev
just setup # creates Python venv, installs all deps
just dev # starts backend + desktop app
```
**Manual setup (all platforms):**
Install [just](https://github.com/casey/just): `brew install just` or `cargo install just`. Run `just --list` to see all commands.
**Prerequisites:** [Bun](https://bun.sh), [Rust](https://rustup.rs), [Python 3.11+](https://python.org), [Tauri Prerequisites](https://v2.tauri.app/start/prerequisites/), and [Xcode](https://developer.apple.com/xcode/) on macOS.
### Building Locally
```bash
# Clone the repo
git clone https://github.com/voicebox-sh/voicebox.git
cd voicebox
# Install dependencies
bun install
# Install Python dependencies
cd backend && pip install -r requirements.txt && cd ..
# Start development
bun run dev
just build # Build CPU server binary + Tauri app
just build-local # (Windows) Build CPU + CUDA server binaries + Tauri app
```
**Prerequisites:** [Bun](https://bun.sh), [Rust](https://rustup.rs), [Python 3.11+](https://python.org).
### Adding New Voice Models
**Performance:**
- **Apple Silicon (M1/M2/M3)**: Uses MLX backend with native Metal acceleration for 4-5x faster inference
- **Windows/Linux/Intel Mac**: Uses PyTorch backend (CUDA GPU recommended, CPU supported but slower)
The multi-engine architecture makes adding new TTS engines straightforward. A [step-by-step guide](docs/content/docs/developer/tts-engines.mdx) covers the full process: dependency research, backend protocol implementation, frontend wiring, and PyInstaller bundling.
The guide is optimized for AI coding agents. An [agent skill](.agents/skills/add-tts-engine/SKILL.md) can pick up a model name and handle the entire integration autonomously — you just test the build locally.
### Project Structure
+3 -3
View File
@@ -6,8 +6,8 @@ We release patches for security vulnerabilities. Which versions are eligible for
| Version | Supported |
| ------- | ------------------ |
| 0.1.x | :white_check_mark: |
| < 0.1 | :x: |
| 0.3.x | :white_check_mark: |
| < 0.3 | :x: |
## Reporting a Vulnerability
@@ -82,7 +82,7 @@ Timeline may vary based on severity and complexity.
## Security Updates
Security updates will be:
- Released as patch versions (e.g., 0.1.1)
- Released as patch versions (e.g., 0.3.2)
- Documented in CHANGELOG.md
- Announced via GitHub releases
- Automatically delivered via auto-updater
+2 -1
View File
@@ -1,11 +1,12 @@
{
"name": "@voicebox/app",
"version": "0.1.11",
"version": "0.4.1",
"private": true,
"type": "module",
"scripts": {
"dev": "vite",
"build": "vite build",
"typecheck": "tsc -p tsconfig.json --noEmit",
"preview": "vite preview",
"lint": "biome lint src",
"lint:fix": "biome lint --write src",
+23
View File
@@ -0,0 +1,23 @@
import { readFileSync } from 'node:fs';
import path from 'node:path';
import type { Plugin } from 'vite';
/** Vite plugin that exposes CHANGELOG.md as `virtual:changelog`. */
export function changelogPlugin(repoRoot: string): Plugin {
const virtualId = 'virtual:changelog';
const resolvedId = '\0' + virtualId;
const changelogPath = path.resolve(repoRoot, 'CHANGELOG.md');
return {
name: 'changelog',
resolveId(id) {
if (id === virtualId) return resolvedId;
},
load(id) {
if (id === resolvedId) {
const raw = readFileSync(changelogPath, 'utf-8');
return `export default ${JSON.stringify(raw)};`;
}
},
};
}
+111 -14
View File
@@ -4,12 +4,42 @@ import voiceboxLogo from '@/assets/voicebox-logo.png';
import ShinyText from '@/components/ShinyText';
import { TitleBarDragRegion } from '@/components/TitleBarDragRegion';
import { useAutoUpdater } from '@/hooks/useAutoUpdater';
import { apiClient } from '@/lib/api/client';
import type { HealthResponse } from '@/lib/api/types';
import { TOP_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import { cn } from '@/lib/utils/cn';
import { usePlatform } from '@/platform/PlatformContext';
import { router } from '@/router';
import { useLogStore } from '@/stores/logStore';
import { useServerStore } from '@/stores/serverStore';
/**
* Validate that a health response has the expected Voicebox-specific shape.
* Prevents misidentifying an unrelated service on the same port.
*/
function isVoiceboxHealthResponse(health: HealthResponse): boolean {
return (
health?.status === 'healthy' &&
typeof health.model_loaded === 'boolean' &&
typeof health.gpu_available === 'boolean'
);
}
/**
* Check whether a startup error indicates the port is occupied by an external
* server (which we should try to reuse via health-check polling) vs. a real
* failure (missing sidecar, signing issue, etc.) that should surface immediately.
*/
function isPortInUseError(error: unknown): boolean {
const msg = error instanceof Error ? error.message : String(error);
return (
msg.includes('already in use') ||
msg.includes('port') ||
msg.includes('EADDRINUSE') ||
msg.includes('address already in use')
);
}
const LOADING_MESSAGES = [
'Warming up tensors...',
'Calibrating synthesizer engine...',
@@ -36,6 +66,7 @@ const LOADING_MESSAGES = [
function App() {
const platform = usePlatform();
const [serverReady, setServerReady] = useState(false);
const [startupError, setStartupError] = useState<string | null>(null);
const [loadingMessageIndex, setLoadingMessageIndex] = useState(0);
const serverStartingRef = useRef(false);
@@ -63,6 +94,14 @@ function App() {
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [platform.lifecycle]);
// Subscribe to server logs
useEffect(() => {
const unsubscribe = platform.lifecycle.subscribeToServerLogs((entry) => {
useLogStore.getState().addEntry(entry);
});
return unsubscribe;
}, [platform.lifecycle]);
// Setup window close handler and auto-start server when running in Tauri (production only)
useEffect(() => {
if (!platform.metadata.isTauri) {
@@ -82,7 +121,6 @@ function App() {
console.log('Dev mode: Skipping auto-start of server (run it separately)');
setServerReady(true); // Mark as ready so UI doesn't show loading screen
// Mark that server was not started by app (so we don't try to stop it on close)
// @ts-expect-error - adding property to window
window.__voiceboxServerStartedByApp = false;
return;
}
@@ -93,24 +131,64 @@ function App() {
}
serverStartingRef.current = true;
console.log('Production mode: Starting bundled server...');
const isRemote = useServerStore.getState().mode === 'remote';
const customModelsDir = useServerStore.getState().customModelsDir;
console.log(`Production mode: Starting bundled server... (remote: ${isRemote})`);
platform.lifecycle
.startServer(false)
.startServer(isRemote, customModelsDir)
.then((serverUrl) => {
console.log('Server is ready at:', serverUrl);
// Update the server URL in the store with the dynamically assigned port
useServerStore.getState().setServerUrl(serverUrl);
setServerReady(true);
// Mark that we started the server (so we know to stop it on close)
// @ts-expect-error - adding property to window
window.__voiceboxServerStartedByApp = true;
})
.catch((error) => {
console.error('Failed to auto-start server:', error);
serverStartingRef.current = false;
// @ts-expect-error - adding property to window
window.__voiceboxServerStartedByApp = false;
// Only fall back to health-check polling when the error indicates the
// port is occupied (likely an external server). For real failures
// (missing sidecar, signing issues, etc.) surface the error immediately.
if (!isPortInUseError(error)) {
const msg = error instanceof Error ? error.message : String(error);
console.error('Real startup failure — not polling:', msg);
setStartupError(msg);
return;
}
// Fall back to polling: the server may already be running externally
// (e.g. started via python/uvicorn/Docker). Poll the health endpoint
// until it responds with a valid Voicebox payload, then transition to
// the main UI.
console.log('Falling back to health-check polling...');
const pollInterval = setInterval(async () => {
try {
const health = await apiClient.getHealth();
if (!isVoiceboxHealthResponse(health)) {
console.log('Health response is not from a Voicebox server, keep polling...');
return;
}
console.log('External Voicebox server detected via health check');
clearInterval(pollInterval);
setServerReady(true);
} catch {
// Server not ready yet, keep polling
}
}, 2000);
// Stop polling after 2 minutes and surface the failure
setTimeout(() => {
clearInterval(pollInterval);
serverStartingRef.current = false;
setStartupError(
'Could not connect to a Voicebox server within 2 minutes. ' +
'Please check that the server is running and try again.',
);
}, 120_000);
});
// Cleanup: stop server on actual unmount (not StrictMode remount)
@@ -157,15 +235,34 @@ function App() {
className="w-48 h-48 object-contain animate-fade-in-scale relative z-10"
/>
</div>
<div className="animate-fade-in-delayed">
<ShinyText
text={LOADING_MESSAGES[loadingMessageIndex]}
className="text-lg font-medium text-muted-foreground"
speed={2}
color="hsl(var(--muted-foreground))"
shineColor="hsl(var(--foreground))"
/>
</div>
{startupError ? (
<div className="animate-fade-in-delayed max-w-md mx-auto space-y-3">
<p className="text-lg font-medium text-destructive">Server startup failed</p>
<p className="text-sm text-muted-foreground">{startupError}</p>
<button
type="button"
className="mt-2 px-4 py-2 text-sm rounded-md bg-primary text-primary-foreground hover:bg-primary/90 transition-colors"
onClick={() => {
setStartupError(null);
serverStartingRef.current = false;
// Trigger a re-mount of the effect by toggling state
window.location.reload();
}}
>
Retry
</button>
</div>
) : (
<div className="animate-fade-in-delayed">
<ShinyText
text={LOADING_MESSAGES[loadingMessageIndex]}
className="text-lg font-medium text-muted-foreground"
speed={2}
color="hsl(var(--muted-foreground))"
shineColor="hsl(var(--foreground))"
/>
</div>
)}
</div>
</div>
);
+7 -3
View File
@@ -1,5 +1,6 @@
import { useRouterState } from '@tanstack/react-router';
import { TitleBarDragRegion } from '@/components/TitleBarDragRegion';
import { AudioKeepAlive } from '@/components/AudioPlayer/AudioKeepAlive';
import { AudioPlayer } from '@/components/AudioPlayer/AudioPlayer';
import { StoryTrackEditor } from '@/components/StoriesTab/StoryTrackEditor';
import { TOP_SAFE_AREA_PADDING } from '@/lib/constants/ui';
@@ -14,16 +15,19 @@ interface AppFrameProps {
export function AppFrame({ children }: AppFrameProps) {
const routerState = useRouterState();
const isStoriesRoute = routerState.location.pathname === '/stories';
const selectedStoryId = useStoryStore((state) => state.selectedStoryId);
const { data: story } = useStory(selectedStoryId);
// Show track editor when on stories route with a selected story that has items
const showTrackEditor = isStoriesRoute && selectedStoryId && story && story.items.length > 0;
return (
<div className={cn('h-screen bg-background flex flex-col overflow-hidden', TOP_SAFE_AREA_PADDING)}>
<div
className={cn('h-screen bg-background flex flex-col overflow-hidden', TOP_SAFE_AREA_PADDING)}
>
<TitleBarDragRegion />
<AudioKeepAlive />
{children}
{showTrackEditor ? (
<StoryTrackEditor storyId={story.id} items={story.items} />
@@ -0,0 +1,85 @@
import { useEffect, useRef } from 'react';
import { debug } from '@/lib/utils/debug';
// WKWebView tears down the app's CoreAudio output when idle for long enough,
// and a JS-level reload (cmd+R) does NOT restore it — only relaunching the
// Tauri app does. Keeping a silent <audio> element looping forever prevents
// the OS audio session from ever going dormant.
//
// Real silence (zero PCM samples) at full volume is preferred over a muted
// element: browsers/WebKit can optimize muted media away, which defeats the
// purpose of holding the session open.
function buildSilentWavUrl(seconds = 1, sampleRate = 8000): string {
const numSamples = seconds * sampleRate;
const bytes = 44 + numSamples * 2;
const buffer = new ArrayBuffer(bytes);
const view = new DataView(buffer);
const write = (offset: number, str: string) => {
for (let i = 0; i < str.length; i++) view.setUint8(offset + i, str.charCodeAt(i));
};
write(0, 'RIFF');
view.setUint32(4, bytes - 8, true);
write(8, 'WAVE');
write(12, 'fmt ');
view.setUint32(16, 16, true);
view.setUint16(20, 1, true);
view.setUint16(22, 1, true);
view.setUint32(24, sampleRate, true);
view.setUint32(28, sampleRate * 2, true);
view.setUint16(32, 2, true);
view.setUint16(34, 16, true);
write(36, 'data');
view.setUint32(40, numSamples * 2, true);
return URL.createObjectURL(new Blob([buffer], { type: 'audio/wav' }));
}
export function AudioKeepAlive() {
const audioRef = useRef<HTMLAudioElement | null>(null);
useEffect(() => {
const url = buildSilentWavUrl(1, 8000);
const el = new Audio(url);
el.loop = true;
el.volume = 1;
el.preload = 'auto';
audioRef.current = el;
const tryPlay = () => {
if (!audioRef.current) return;
if (!audioRef.current.paused) return;
audioRef.current.play().catch((err) => {
debug.log('[AudioKeepAlive] play blocked (will retry on next gesture):', err);
});
};
tryPlay();
// Autoplay may be blocked until first user interaction — re-attempt then.
const onGesture = () => tryPlay();
window.addEventListener('pointerdown', onGesture, { once: false });
window.addEventListener('keydown', onGesture, { once: false });
// If the webview ever pauses the element on background, resume on return.
const onWake = () => {
if (!document.hidden) tryPlay();
};
document.addEventListener('visibilitychange', onWake);
window.addEventListener('focus', onWake);
window.addEventListener('pageshow', onWake);
return () => {
window.removeEventListener('pointerdown', onGesture);
window.removeEventListener('keydown', onGesture);
document.removeEventListener('visibilitychange', onWake);
window.removeEventListener('focus', onWake);
window.removeEventListener('pageshow', onWake);
el.pause();
el.src = '';
URL.revokeObjectURL(url);
audioRef.current = null;
};
}, []);
return null;
}
+219 -505
View File
@@ -1,22 +1,22 @@
import { useQuery } from '@tanstack/react-query';
import { Pause, Play, Repeat, Volume2, VolumeX, X } from 'lucide-react';
import { useEffect, useMemo, useRef, useState } from 'react';
import { useEffect, useId, useMemo, useRef, useState } from 'react';
import WaveSurfer from 'wavesurfer.js';
import { Button } from '@/components/ui/button';
import { Slider } from '@/components/ui/slider';
import { apiClient } from '@/lib/api/client';
import { formatAudioDuration } from '@/lib/utils/audio';
import { debug } from '@/lib/utils/debug';
import { usePlayerStore } from '@/stores/playerStore';
import { usePlatform } from '@/platform/PlatformContext';
import { usePlayerStore } from '@/stores/playerStore';
export function AudioPlayer() {
const platform = usePlatform();
const volumeLabelId = useId();
const {
audioUrl,
audioId,
profileId,
title,
isPlaying,
currentTime,
duration,
@@ -62,7 +62,7 @@ export function AudioPlayer() {
);
return shouldUseNative;
}, [profileChannels, channels, profileId]);
}, [profileChannels, channels, platform.metadata.isTauri]);
const waveformRef = useRef<HTMLDivElement>(null);
const wavesurferRef = useRef<WaveSurfer | null>(null);
@@ -72,31 +72,21 @@ export function AudioPlayer() {
const isUsingNativePlaybackRef = useRef(false);
const [isLoading, setIsLoading] = useState(false);
const [error, setError] = useState<string | null>(null);
const [wsReady, setWsReady] = useState(false);
// Initialize WaveSurfer (only when audioUrl exists and container is ready)
// Create WaveSurfer once when the player becomes visible (audioUrl is set).
// This instance is reused for all subsequent audio loads - never destroyed until unmount.
useEffect(() => {
// Don't initialize if no audioUrl or already initialized
if (!audioUrl) {
return;
}
if (!audioUrl) return;
if (wavesurferRef.current) return; // already created
if (wavesurferRef.current) {
debug.log('WaveSurfer already initialized, skipping');
return;
}
debug.log('Creating NEW WaveSurfer instance');
// Wait for container to be properly rendered
const initWaveSurfer = () => {
const container = waveformRef.current;
if (!container) {
// Container not ready yet, retry
setTimeout(initWaveSurfer, 50);
return;
}
// Check if container has dimensions and is visible
const rect = container.getBoundingClientRect();
const style = window.getComputedStyle(container);
const isVisible =
@@ -106,488 +96,221 @@ export function AudioPlayer() {
style.visibility !== 'hidden';
if (!isVisible) {
// Retry after a short delay
setTimeout(initWaveSurfer, 50);
return;
}
debug.log('Initializing WaveSurfer...', {
container,
debug.log('Creating WaveSurfer instance', {
width: rect.width,
height: rect.height,
});
try {
// Get computed CSS variable values
const root = document.documentElement;
const getCSSVar = (varName: string) => {
const value = getComputedStyle(root).getPropertyValue(varName).trim();
return value ? `hsl(${value})` : '';
};
const waveColor = getCSSVar('--muted');
const progressColor = getCSSVar('--accent');
const cursorColor = getCSSVar('--accent');
const wavesurfer = WaveSurfer.create({
container: container,
waveColor: waveColor,
progressColor: progressColor,
cursorColor: cursorColor,
container,
waveColor: getCSSVar('--muted'),
progressColor: getCSSVar('--accent'),
cursorColor: getCSSVar('--accent'),
cursorWidth: 3,
barWidth: 2,
barRadius: 2,
height: 80,
normalize: true,
interact: true,
dragToSeek: { debounceTime: 0 },
mediaControls: false,
backend: 'WebAudio',
interact: true, // Enable interaction (click to seek)
mediaControls: false, // Don't show native controls
});
// Wire up event handlers (these persist for the lifetime of the instance)
wavesurfer.on('timeupdate', (time) => {
const dur = usePlayerStore.getState().duration;
if (dur > 0 && time >= dur) {
setCurrentTime(dur);
const loop = usePlayerStore.getState().isLooping;
if (loop) {
wavesurfer.seekTo(0);
wavesurfer.play().catch((err) => debug.error('Loop play failed:', err));
} else {
wavesurfer.pause();
setIsPlaying(false);
}
return;
}
setCurrentTime(time);
});
wavesurfer.on('ready', () => {
const dur = wavesurfer.getDuration();
setDuration(dur);
loadingRef.current = false;
setIsLoading(false);
setError(null);
debug.log('Audio ready, duration:', dur);
wavesurfer.setVolume(usePlayerStore.getState().volume);
wavesurfer.setMuted(false);
// Auto-play if the flag is set (story mode advance or explicit play)
const shouldAutoPlayNow = usePlayerStore.getState().shouldAutoPlay;
if (shouldAutoPlayNow) {
usePlayerStore.getState().clearAutoPlayFlag();
wavesurfer.play().catch((err) => {
debug.error('Failed to autoplay:', err);
});
} else {
debug.log('Skipping auto-play - shouldAutoPlay is false');
}
});
wavesurfer.on('play', () => setIsPlaying(true));
wavesurfer.on('pause', () => {
setIsPlaying(false);
setCurrentTime(wavesurfer.getCurrentTime());
});
wavesurfer.on('seeking', (time) => setCurrentTime(time));
// Mute audio during drag-to-seek to prevent popping from the WebAudio
// backend's hard stop/start cycle on each seek. Unmute with a short
// fade-in when the drag ends.
const seekMedia = wavesurfer.getMediaElement() as any;
const seekGain: GainNode | null = seekMedia?.getGainNode?.() ?? null;
if (seekGain) {
const ctx = seekGain.context as AudioContext;
wavesurfer.on('dragstart', () => {
seekGain.gain.cancelScheduledValues(ctx.currentTime);
seekGain.gain.setTargetAtTime(0, ctx.currentTime, 0.002);
});
wavesurfer.on('dragend', () => {
seekGain.gain.cancelScheduledValues(ctx.currentTime);
seekGain.gain.setTargetAtTime(1, ctx.currentTime, 0.01);
});
}
wavesurfer.on('finish', () => {
const loop = usePlayerStore.getState().isLooping;
if (loop) {
wavesurfer.seekTo(0);
wavesurfer.play().catch((err) => debug.error('Loop play failed:', err));
} else {
setIsPlaying(false);
const onFinish = usePlayerStore.getState().onFinish;
if (onFinish) onFinish();
}
});
wavesurfer.on('error', (err) => {
debug.error('WaveSurfer error:', err);
setIsLoading(false);
setError(`Audio error: ${err instanceof Error ? err.message : String(err)}`);
});
wavesurfer.on('loading', (percent) => {
setIsLoading(true);
if (percent === 100) setIsLoading(false);
});
wavesurferRef.current = wavesurfer;
setWsReady(true);
debug.log('WaveSurfer created successfully');
} catch (error) {
debug.error('Failed to create WaveSurfer:', error);
} catch (err) {
debug.error('Failed to create WaveSurfer:', err);
setError(
`Failed to initialize waveform: ${error instanceof Error ? error.message : String(error)}`,
`Failed to initialize waveform: ${err instanceof Error ? err.message : String(err)}`,
);
return;
}
const wavesurfer = wavesurferRef.current;
if (!wavesurfer) return;
// Update store when time changes
wavesurfer.on('timeupdate', (time) => {
setCurrentTime(time);
});
// Update store when duration is loaded
wavesurfer.on('ready', async () => {
const dur = wavesurfer.getDuration();
setDuration(dur);
loadingRef.current = false;
setIsLoading(false);
setError(null);
debug.log('Audio ready, duration:', dur);
debug.log('Waveform should be visible now');
// Ensure volume is set
const currentVolume = usePlayerStore.getState().volume;
wavesurfer.setVolume(currentVolume);
// Get the underlying audio element and ensure it's not muted
// (unless we're using native playback, which will be set later)
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement && !isUsingNativePlaybackRef.current) {
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log('Audio element volume:', mediaElement.volume, 'muted:', mediaElement.muted);
}
// Auto-play when ready - check if we should use native playback
// Get current values from the store and queries at runtime (not captured closure values)
const currentAudioUrl = usePlayerStore.getState().audioUrl;
const currentProfileId = usePlayerStore.getState().profileId;
debug.log('Auto-play check - capturing runtime values...');
// Fetch profile channels at runtime (not using captured value)
let runtimeProfileChannels = null;
let runtimeChannels = null;
if (platform.metadata.isTauri && currentProfileId) {
try {
runtimeProfileChannels = await apiClient.getProfileChannels(currentProfileId);
debug.log('Runtime profileChannels:', runtimeProfileChannels);
if (runtimeProfileChannels && runtimeProfileChannels.channel_ids.length > 0) {
runtimeChannels = await apiClient.listChannels();
debug.log('Runtime channels:', runtimeChannels);
}
} catch (error) {
debug.error('Failed to fetch runtime channel data:', error);
}
}
debug.log('Auto-play check:', {
isTauri: platform.metadata.isTauri,
currentAudioUrl,
currentProfileId,
hasProfileChannels: !!runtimeProfileChannels,
hasChannels: !!runtimeChannels,
});
if (
platform.metadata.isTauri &&
currentAudioUrl &&
currentProfileId &&
runtimeProfileChannels &&
runtimeChannels
) {
debug.log('Attempting native audio playback...');
// Stop any existing native playback first
if (isUsingNativePlaybackRef.current) {
try {
platform.audio.stopPlayback();
debug.log('Stopped existing native playback before starting new one');
} catch (error) {
debug.error('Failed to stop existing playback:', error);
}
}
try {
// Collect all device IDs from assigned channels
const assignedChannels = runtimeChannels.filter((ch: any) =>
runtimeProfileChannels.channel_ids.includes(ch.id),
);
debug.log('Assigned channels for playback:', assignedChannels);
// Check if any assigned channel has non-default devices
const shouldUseNative = assignedChannels.some(
(ch: any) => ch.device_ids.length > 0 && !ch.is_default,
);
debug.log('Should use native playback:', shouldUseNative);
if (!shouldUseNative) {
debug.log('No custom devices assigned, falling back to WaveSurfer');
// Reset native playback flag and unmute WaveSurfer
isUsingNativePlaybackRef.current = false;
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'WaveSurfer unmuted for normal playback - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
} else {
const deviceIds = assignedChannels.flatMap((ch: any) => ch.device_ids);
debug.log('Device IDs to play to:', deviceIds);
if (deviceIds.length > 0) {
debug.log('Fetching audio data from:', currentAudioUrl);
// Fetch audio data
const response = await fetch(currentAudioUrl);
const audioData = new Uint8Array(await response.arrayBuffer());
debug.log('Audio data size:', audioData.length);
// Play via native audio
debug.log('Invoking play_audio_to_devices...');
try {
await platform.audio.playToDevices(audioData, deviceIds);
debug.log('play_audio_to_devices completed successfully');
// Mark that we're using native playback
isUsingNativePlaybackRef.current = true;
// Mute WaveSurfer's audio element to prevent UI audio output
// Keep WaveSurfer running for visualization
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
mediaElement.volume = 0;
mediaElement.muted = true;
debug.log(
'WaveSurfer muted for native playback - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
// Start WaveSurfer playback for visualization (muted)
wavesurfer.play().catch((error) => {
debug.error('Failed to start WaveSurfer visualization:', error);
});
setIsPlaying(true);
debug.log('Auto-playing via native audio routing - SUCCESS');
return;
} catch (invokeError) {
debug.error('play_audio_to_devices invoke failed:', invokeError);
throw invokeError;
}
} else {
debug.log('No device IDs found, falling back to WaveSurfer');
}
}
} catch (error) {
debug.error(
'Native playback failed during auto-play, falling back to WaveSurfer:',
error,
);
// Reset native playback flag and unmute WaveSurfer
isUsingNativePlaybackRef.current = false;
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'WaveSurfer unmuted after native playback failure - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
// Fall through to WaveSurfer playback
}
} else {
debug.log('Not using native playback, using WaveSurfer');
// Reset native playback flag and unmute WaveSurfer
isUsingNativePlaybackRef.current = false;
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'WaveSurfer unmuted for normal playback - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
}
// Only auto-play if shouldAutoPlay flag is set (user explicitly clicked to play)
const shouldAutoPlayNow = usePlayerStore.getState().shouldAutoPlay;
if (shouldAutoPlayNow) {
// Clear the flag first
usePlayerStore.getState().clearAutoPlayFlag();
// Use a small delay to ensure audio element is fully ready
setTimeout(() => {
wavesurfer.play().catch((error) => {
debug.error('Failed to autoplay:', error);
// Don't show error for autoplay failures (browser restrictions)
});
}, 100);
} else {
debug.log('Skipping auto-play - shouldAutoPlay is false');
}
});
// Handle play/pause
wavesurfer.on('play', () => {
setIsPlaying(true);
// Ensure audio element volume is set correctly
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
// Double-check: if using native playback, keep WaveSurfer muted
// Otherwise, ensure it's unmuted
if (isUsingNativePlaybackRef.current) {
mediaElement.volume = 0;
mediaElement.muted = true;
debug.log('Playing (native mode) - WaveSurfer muted for visualization only');
} else {
// Ensure WaveSurfer is unmuted for normal playback
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'Playing (normal mode) - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
}
});
wavesurfer.on('pause', () => setIsPlaying(false));
wavesurfer.on('finish', () => {
// Check loop state from store
const loop = usePlayerStore.getState().isLooping;
if (loop) {
wavesurfer.seekTo(0);
wavesurfer.play();
} else {
setIsPlaying(false);
// Trigger finish callback if set
const onFinish = usePlayerStore.getState().onFinish;
if (onFinish) {
onFinish();
}
}
});
// Handle errors
wavesurfer.on('error', (error) => {
debug.error('WaveSurfer error:', error);
setIsLoading(false);
setError(`Audio error: ${error instanceof Error ? error.message : String(error)}`);
});
// Handle loading
wavesurfer.on('loading', (percent) => {
setIsLoading(true);
if (percent === 100) {
setIsLoading(false);
}
});
// Load audio immediately if audioUrl is already set
if (audioUrl) {
debug.log('WaveSurfer ready, loading audio:', audioUrl);
loadingRef.current = true;
setIsLoading(true);
// Stop any current playback before loading new audio
if (wavesurfer.isPlaying()) {
wavesurfer.pause();
}
wavesurfer
.load(audioUrl)
.then(() => {
debug.log('Audio loaded into WaveSurfer');
loadingRef.current = false;
})
.catch((error) => {
debug.error('Failed to load audio into WaveSurfer:', error);
loadingRef.current = false;
setIsLoading(false);
setError(
`Failed to load audio: ${error instanceof Error ? error.message : String(error)}`,
);
});
}
};
// Use double requestAnimationFrame to ensure DOM is fully rendered
let rafId1: number;
let rafId2: number;
let timeoutId: number | null = null;
rafId1 = requestAnimationFrame(() => {
rafId2 = requestAnimationFrame(() => {
// Add a small delay to ensure container is fully laid out
timeoutId = setTimeout(() => {
initWaveSurfer();
}, 10);
});
let rafId: number;
rafId = requestAnimationFrame(() => {
initWaveSurfer();
});
return () => {
debug.log('Cleaning up WaveSurfer initialization effect');
if (rafId1) cancelAnimationFrame(rafId1);
if (rafId2) cancelAnimationFrame(rafId2);
if (timeoutId) clearTimeout(timeoutId);
cancelAnimationFrame(rafId);
};
// Only run on mount-like conditions. audioUrl is here so we create the instance
// when the player first appears, but we guard against re-creation above.
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [audioUrl, setIsPlaying, setDuration, setCurrentTime]);
// Destroy WaveSurfer only on unmount
useEffect(() => {
return () => {
if (wavesurferRef.current) {
debug.log('Destroying WaveSurfer instance');
debug.log('Destroying WaveSurfer instance (unmount)');
try {
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
mediaElement.pause();
mediaElement.src = '';
}
wavesurferRef.current.destroy();
} catch (error) {
debug.error('Error destroying WaveSurfer:', error);
} catch (err) {
debug.error('Error destroying WaveSurfer:', err);
}
wavesurferRef.current = null;
setWsReady(false);
}
};
}, [audioUrl, setIsPlaying, setCurrentTime, setDuration]);
}, []);
// Load audio when URL changes (only if WaveSurfer is already initialized)
// Load audio when URL changes (reuses the existing WaveSurfer instance)
useEffect(() => {
const wavesurfer = wavesurferRef.current;
if (!wavesurfer || !wsReady) return;
if (!audioUrl || !wavesurfer) {
// Reset state when no audio or WaveSurfer not ready
if (!audioUrl && wavesurfer) {
wavesurfer.pause();
wavesurfer.seekTo(0);
loadingRef.current = false;
setIsLoading(false);
setDuration(0);
setCurrentTime(0);
setError(null);
// Reset native playback flag
isUsingNativePlaybackRef.current = false;
}
if (!audioUrl) {
// No audio - pause and reset
wavesurfer.pause();
wavesurfer.seekTo(0);
loadingRef.current = false;
setIsLoading(false);
setDuration(0);
setCurrentTime(0);
setError(null);
isUsingNativePlaybackRef.current = false;
return;
}
// Stop native playback if it was active
if (isUsingNativePlaybackRef.current && platform.metadata.isTauri) {
try {
platform.audio.stopPlayback();
debug.log('Stopped native audio playback');
} catch (error) {
debug.error('Failed to stop native playback:', error);
}
}
// Reset native playback flag when loading new audio
// Also unmute WaveSurfer if it was muted
if (isUsingNativePlaybackRef.current) {
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
mediaElement.muted = false;
mediaElement.volume = usePlayerStore.getState().volume;
}
}
// Reset native playback state
isUsingNativePlaybackRef.current = false;
wavesurfer.setMuted(false);
wavesurfer.setVolume(usePlayerStore.getState().volume);
// CRITICAL: Force stop any current playback and cancel any pending loads
// This must happen BEFORE any early returns
debug.log('Audio URL changed to:', audioUrl);
// COMPLETELY stop and destroy the current audio
// Stop current playback and reset position before loading new audio.
// With the WebAudio backend, pause() accumulates playedDuration internally.
// seekTo(0) resets it so the new track starts from the beginning.
debug.log('Loading new audio URL:', audioUrl);
try {
// First pause if playing
if (wavesurfer.isPlaying()) {
debug.log('Pausing current playback');
wavesurfer.pause();
}
// Stop the media element explicitly
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
debug.log('Stopping media element');
mediaElement.pause();
mediaElement.currentTime = 0;
mediaElement.src = '';
}
// Use empty() to completely destroy the waveform and media element
debug.log('Calling wavesurfer.empty() to destroy audio');
wavesurfer.empty();
} catch (error) {
debug.error('Error stopping previous audio:', error);
// Continue anyway to load new audio
wavesurfer.seekTo(0);
} catch (err) {
debug.error('Error resetting before load:', err);
}
// Reset loading state to allow new load (cancel any pending loads)
loadingRef.current = false;
// Now start the new load
loadingRef.current = true;
setIsLoading(true);
setError(null);
setCurrentTime(0);
setDuration(0);
// Load new audio
debug.log('Starting new audio load for:', audioUrl);
wavesurfer
.load(audioUrl)
.then(() => {
debug.log('Audio load promise resolved');
// Don't set loading to false here - wait for 'ready' event
debug.log('Audio loaded into WaveSurfer');
loadingRef.current = false;
})
.catch((error) => {
debug.error('Failed to load audio:', error);
debug.error('Audio URL:', audioUrl);
.catch((err) => {
debug.error('Failed to load audio:', err);
loadingRef.current = false;
setIsLoading(false);
setError(`Failed to load audio: ${error instanceof Error ? error.message : String(error)}`);
setError(`Failed to load audio: ${err instanceof Error ? err.message : String(err)}`);
});
}, [audioUrl, setCurrentTime, setDuration]);
}, [audioUrl, wsReady, setCurrentTime, setDuration]);
// Sync play/pause state (only when user clicks play/pause button, not auto-sync)
// This effect is kept for external state changes but should be minimal
@@ -595,7 +318,6 @@ export function AudioPlayer() {
if (!wavesurferRef.current || duration === 0) return;
if (isPlaying && wavesurferRef.current.isPlaying() === false) {
// Only auto-play if audio is ready
wavesurferRef.current.play().catch((error) => {
debug.error('Failed to play:', error);
setIsPlaying(false);
@@ -610,20 +332,6 @@ export function AudioPlayer() {
useEffect(() => {
if (wavesurferRef.current) {
wavesurferRef.current.setVolume(volume);
// Also ensure the underlying audio element volume is set
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
// If using native playback, keep WaveSurfer muted regardless of volume setting
if (isUsingNativePlaybackRef.current) {
mediaElement.volume = 0;
mediaElement.muted = true;
debug.log('Volume sync: Using native playback, keeping WaveSurfer muted');
} else {
mediaElement.volume = volume;
mediaElement.muted = volume === 0;
debug.log('Volume synced:', volume, 'muted:', mediaElement.muted);
}
}
}
}, [volume]);
@@ -648,7 +356,6 @@ export function AudioPlayer() {
return;
}
// Reset to beginning and play
debug.log('Restarting current audio from beginning');
wavesurfer.seekTo(0);
wavesurfer.play().catch((error) => {
@@ -657,34 +364,35 @@ export function AudioPlayer() {
setError(`Playback error: ${error instanceof Error ? error.message : String(error)}`);
});
// Clear the restart flag
clearRestartFlag();
}, [shouldRestart, duration, setIsPlaying, clearRestartFlag]);
// Handle shouldAutoPlay flag - for story mode auto-advance
const shouldAutoPlay = usePlayerStore((state) => state.shouldAutoPlay);
const clearAutoPlayFlag = usePlayerStore((state) => state.clearAutoPlayFlag);
// Auto-play is handled exclusively in the WaveSurfer 'ready' event handler.
// A separate effect here would race with the ready event since the WebAudio
// backend needs to fully decode the audio before play() works correctly.
// Spacebar to play/pause (capture phase so it fires before focused elements)
useEffect(() => {
const wavesurfer = wavesurferRef.current;
if (!wavesurfer || !shouldAutoPlay || duration === 0) {
return;
}
// Auto-play the newly loaded audio
debug.log('Auto-playing next track in story mode');
wavesurfer.seekTo(0);
wavesurfer.play().catch((error) => {
debug.error('Failed to auto-play:', error);
setIsPlaying(false);
setError(`Playback error: ${error instanceof Error ? error.message : String(error)}`);
});
// Clear the auto-play flag
clearAutoPlayFlag();
}, [shouldAutoPlay, duration, setIsPlaying, clearAutoPlayFlag]);
// Handle loop - WaveSurfer handles this via the 'finish' event
const onKeyDown = (e: KeyboardEvent) => {
if (e.code !== 'Space') return;
// Ignore if user is typing in an input/textarea
const tag = (e.target as HTMLElement)?.tagName;
if (tag === 'INPUT' || tag === 'TEXTAREA' || (e.target as HTMLElement)?.isContentEditable) {
return;
}
if (audioUrl && duration > 0 && wavesurferRef.current) {
e.preventDefault();
e.stopPropagation();
if (wavesurferRef.current.isPlaying()) {
wavesurferRef.current.pause();
} else {
wavesurferRef.current.play().catch((err) => debug.error('Spacebar play failed:', err));
}
}
};
document.addEventListener('keydown', onKeyDown, true);
return () => document.removeEventListener('keydown', onKeyDown, true);
}, [audioUrl, duration]);
const handlePlayPause = async () => {
// Standard WaveSurfer playback (works for both normal and native playback modes)
@@ -743,11 +451,8 @@ export function AudioPlayer() {
isUsingNativePlaybackRef.current = true;
// Mute WaveSurfer and start it for visualization
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
mediaElement.volume = 0;
mediaElement.muted = true;
}
wavesurferRef.current.setVolume(0);
wavesurferRef.current.setMuted(true);
// Start WaveSurfer for visualization (muted)
wavesurferRef.current.play().catch((error) => {
@@ -771,11 +476,8 @@ export function AudioPlayer() {
} else {
// Ensure WaveSurfer is not muted if not using native playback
if (!isUsingNativePlaybackRef.current) {
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
mediaElement.muted = false;
mediaElement.volume = volume;
}
wavesurferRef.current.setMuted(false);
wavesurferRef.current.setVolume(volume);
}
wavesurferRef.current.play().catch((error) => {
@@ -829,27 +531,32 @@ export function AudioPlayer() {
size="icon"
onClick={handlePlayPause}
disabled={isLoading || duration === 0}
className="shrink-0"
className={`shrink-0 -mt-2 ${isPlaying ? 'bg-accent text-accent-foreground' : ''}`}
title={duration === 0 && !isLoading ? 'Audio not loaded' : ''}
aria-label={
duration === 0 && !isLoading ? 'Audio not loaded' : isPlaying ? 'Pause' : 'Play'
}
>
{isPlaying ? <Pause className="h-5 w-5" /> : <Play className="h-5 w-5" />}
{isPlaying ? (
<Pause className="h-5 w-5 fill-current" />
) : (
<Play className="h-5 w-5 fill-current" />
)}
</Button>
{/* Waveform */}
<div className="flex-1 min-w-0 flex flex-col gap-1">
<div ref={waveformRef} className="w-full min-h-[80px]" />
{duration > 0 && (
<Slider
value={duration > 0 ? [(currentTime / duration) * 100] : [0]}
onValueChange={handleSeek}
max={100}
step={0.1}
className="w-full"
/>
)}
{isLoading && (
<div className="text-xs text-muted-foreground text-center py-2">Loading audio...</div>
)}
<div ref={waveformRef} className="w-full min-h-[80px] select-none" />
<Slider
value={duration > 0 ? [(currentTime / duration) * 100] : [0]}
onValueChange={handleSeek}
max={100}
step={0.1}
className="w-full"
aria-label="Playback position"
aria-valuetext={`${formatAudioDuration(currentTime)} of ${formatAudioDuration(duration)}`}
/>
{error && <div className="text-xs text-destructive text-center py-2">{error}</div>}
</div>
@@ -860,38 +567,44 @@ export function AudioPlayer() {
<span className="font-mono">{formatAudioDuration(duration)}</span>
</div>
{/* Title */}
{title && (
<div className="text-sm font-medium truncate max-w-[200px] shrink-0">{title}</div>
)}
{/* Loop Button */}
<Button
variant="ghost"
size="icon"
onClick={toggleLoop}
className={isLooping ? 'text-primary' : ''}
className={isLooping ? 'bg-accent text-accent-foreground' : ''}
title="Toggle loop"
aria-label={isLooping ? 'Stop looping' : 'Loop'}
>
<Repeat className="h-4 w-4" />
</Button>
{/* Volume Control */}
<div className="flex items-center gap-2 shrink-0 w-[120px]">
<div
className="flex items-center gap-2 shrink-0 w-[120px]"
role="group"
aria-label="Volume"
>
<Button
variant="ghost"
size="icon"
onClick={() => setVolume(volume > 0 ? 0 : 1)}
className="h-8 w-8"
aria-label={volume > 0 ? 'Mute' : 'Unmute'}
>
{volume > 0 ? <Volume2 className="h-4 w-4" /> : <VolumeX className="h-4 w-4" />}
</Button>
<span id={volumeLabelId} className="sr-only">
Volume level, {Math.round(volume * 100)}%
</span>
<Slider
value={[volume * 100]}
onValueChange={handleVolumeChange}
max={100}
step={1}
className="flex-1"
aria-labelledby={volumeLabelId}
aria-valuetext={`${Math.round(volume * 100)}%`}
/>
</div>
@@ -902,6 +615,7 @@ export function AudioPlayer() {
onClick={handleClose}
className="shrink-0"
title="Close player"
aria-label="Close player"
>
<X className="h-5 w-5" />
</Button>
+13 -9
View File
@@ -23,8 +23,8 @@ import {
import { apiClient } from '@/lib/api/client';
import { BOTTOM_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import { cn } from '@/lib/utils/cn';
import { usePlayerStore } from '@/stores/playerStore';
import { usePlatform } from '@/platform/PlatformContext';
import { usePlayerStore } from '@/stores/playerStore';
interface AudioDevice {
id: string;
@@ -124,6 +124,13 @@ export function AudioTab() {
);
}
const handleChannelDelete = async (e: React.MouseEvent, channelId: string) => {
e.stopPropagation();
if (await confirm('Delete this channel?')) {
deleteChannel.mutate(channelId);
}
};
const allChannels = channels || [];
const allDevices = devices || [];
const selectedChannel = selectedChannelId
@@ -161,7 +168,7 @@ export function AudioTab() {
</Button>
</div>
) : (
<div className="space-y-3 p-2">
<div className="space-y-3">
{allChannels.map((channel) => {
const isSelected = selectedChannelId === channel.id;
return (
@@ -241,12 +248,7 @@ export function AudioTab() {
variant="ghost"
size="sm"
className="h-8 w-8 p-0"
onClick={(e) => {
e.stopPropagation();
if (confirm('Delete this channel?')) {
deleteChannel.mutate(channel.id);
}
}}
onClick={(e) => handleChannelDelete(e, channel.id)}
>
<Trash2 className="h-4 w-4" />
</Button>
@@ -341,7 +343,9 @@ export function AudioTab() {
<div className="flex flex-col items-center justify-center py-12 border-2 border-dashed border-muted rounded-md">
<CheckCircle2 className="h-12 w-12 text-muted-foreground mb-4" />
<p className="text-muted-foreground text-center">
{platform.metadata.isTauri ? 'No audio devices found' : 'Audio device selection requires Tauri'}
{platform.metadata.isTauri
? 'No audio devices found'
: 'Audio device selection requires Tauri'}
</p>
</div>
)}
@@ -0,0 +1,377 @@
import {
closestCenter,
DndContext,
type DragEndEvent,
KeyboardSensor,
PointerSensor,
useSensor,
useSensors,
} from '@dnd-kit/core';
import {
arrayMove,
SortableContext,
sortableKeyboardCoordinates,
useSortable,
verticalListSortingStrategy,
} from '@dnd-kit/sortable';
import { CSS } from '@dnd-kit/utilities';
import { useQuery } from '@tanstack/react-query';
import { ChevronDown, ChevronRight, GripVertical, Plus, Power, Trash2 } from 'lucide-react';
import { useCallback, useMemo, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import { Label } from '@/components/ui/label';
import {
Select,
SelectContent,
SelectItem,
SelectTrigger,
SelectValue,
} from '@/components/ui/select';
import { Slider } from '@/components/ui/slider';
import { apiClient } from '@/lib/api/client';
import type { AvailableEffect, EffectConfig, EffectPresetResponse } from '@/lib/api/types';
import { cn } from '@/lib/utils/cn';
// Each effect in the chain gets a stable ID for dnd-kit
interface EffectWithId extends EffectConfig {
_id: string;
}
let nextId = 0;
function makeId() {
return `fx-${++nextId}`;
}
interface EffectsChainEditorProps {
value: EffectConfig[];
onChange: (chain: EffectConfig[]) => void;
compact?: boolean;
showPresets?: boolean;
}
export function EffectsChainEditor({
value,
onChange,
compact = false,
showPresets = true,
}: EffectsChainEditorProps) {
const [expandedId, setExpandedId] = useState<string | null>(null);
// Maintain stable IDs for each effect across renders.
// We use a ref to map value items to IDs, rebuilding when length changes.
const idsRef = useRef<string[]>([]);
const items: EffectWithId[] = useMemo(() => {
// Grow ID array if effects were added
while (idsRef.current.length < value.length) {
idsRef.current.push(makeId());
}
// Shrink if effects were removed
if (idsRef.current.length > value.length) {
idsRef.current = idsRef.current.slice(0, value.length);
}
return value.map((e, i) => ({ ...e, _id: idsRef.current[i] }));
}, [value]);
const sensors = useSensors(
useSensor(PointerSensor, { activationConstraint: { distance: 5 } }),
useSensor(KeyboardSensor, { coordinateGetter: sortableKeyboardCoordinates }),
);
const { data: availableEffects } = useQuery({
queryKey: ['available-effects'],
queryFn: () => apiClient.getAvailableEffects(),
staleTime: Infinity,
});
const { data: presets } = useQuery({
queryKey: ['effect-presets'],
queryFn: () => apiClient.listEffectPresets(),
staleTime: 30_000,
});
const effectsMap = useMemo(() => {
const m = new Map<string, AvailableEffect>();
if (availableEffects) {
for (const e of availableEffects.effects) {
m.set(e.type, e);
}
}
return m;
}, [availableEffects]);
function addEffect(type: string) {
const def = effectsMap.get(type);
if (!def) return;
const params: Record<string, number> = {};
for (const [key, p] of Object.entries(def.params)) {
params[key] = p.default;
}
const newEffect: EffectConfig = { type, enabled: true, params };
const newId = makeId();
idsRef.current = [...idsRef.current, newId];
onChange([...value, newEffect]);
setExpandedId(newId);
}
const removeEffect = useCallback(
(index: number) => {
const removedId = idsRef.current[index];
idsRef.current = idsRef.current.filter((_, i) => i !== index);
onChange(value.filter((_, i) => i !== index));
if (expandedId === removedId) setExpandedId(null);
},
[value, onChange, expandedId],
);
const toggleEnabled = useCallback(
(index: number) => {
onChange(value.map((e, i) => (i === index ? { ...e, enabled: !e.enabled } : e)));
},
[value, onChange],
);
const updateParam = useCallback(
(index: number, paramName: string, paramValue: number) => {
onChange(
value.map((e, i) =>
i === index ? { ...e, params: { ...e.params, [paramName]: paramValue } } : e,
),
);
},
[value, onChange],
);
function loadPreset(preset: EffectPresetResponse) {
idsRef.current = preset.effects_chain.map(() => makeId());
onChange(preset.effects_chain);
setExpandedId(null);
}
function clearAll() {
idsRef.current = [];
onChange([]);
setExpandedId(null);
}
function handleDragEnd(event: DragEndEvent) {
const { active, over } = event;
if (!over || active.id === over.id) return;
const oldIndex = idsRef.current.indexOf(active.id as string);
const newIndex = idsRef.current.indexOf(over.id as string);
if (oldIndex === -1 || newIndex === -1) return;
idsRef.current = arrayMove(idsRef.current, oldIndex, newIndex);
onChange(arrayMove([...value], oldIndex, newIndex));
}
return (
<div className={cn('space-y-2', compact && 'text-sm')}>
{/* Preset selector row */}
{showPresets && (
<div className="flex items-center gap-2">
<Select
onValueChange={(id) => {
const preset = presets?.find((p) => p.id === id);
if (preset) loadPreset(preset);
}}
>
<SelectTrigger className="h-8 flex-1 text-xs focus:ring-0 focus:ring-offset-0">
<SelectValue placeholder="Load preset..." />
</SelectTrigger>
<SelectContent>
{presets?.map((p) => (
<SelectItem key={p.id} value={p.id}>
{p.name}
{p.description && (
<span className="ml-1 text-muted-foreground">- {p.description}</span>
)}
</SelectItem>
))}
</SelectContent>
</Select>
{value.length > 0 && (
<Button
variant="ghost"
size="sm"
className="h-8 px-2 text-xs text-muted-foreground"
onClick={clearAll}
>
Clear
</Button>
)}
</div>
)}
{/* Sortable effects chain */}
<DndContext sensors={sensors} collisionDetection={closestCenter} onDragEnd={handleDragEnd}>
<SortableContext items={items.map((i) => i._id)} strategy={verticalListSortingStrategy}>
{items.map((effect, index) => (
<SortableEffectItem
key={effect._id}
id={effect._id}
effect={effect}
index={index}
effectDef={effectsMap.get(effect.type)}
isExpanded={expandedId === effect._id}
onToggleExpand={() => setExpandedId(expandedId === effect._id ? null : effect._id)}
onRemove={() => removeEffect(index)}
onToggleEnabled={() => toggleEnabled(index)}
onUpdateParam={(paramName, paramValue) => updateParam(index, paramName, paramValue)}
/>
))}
</SortableContext>
</DndContext>
{/* Add effect */}
{availableEffects && (
<Select onValueChange={addEffect}>
<SelectTrigger className="h-8 border-dashed text-xs text-muted-foreground focus:ring-0 focus:ring-offset-0">
<Plus className="mr-1 h-3.5 w-3.5" />
<SelectValue placeholder="Add effect..." />
</SelectTrigger>
<SelectContent>
{availableEffects.effects.map((e) => (
<SelectItem key={e.type} value={e.type}>
{e.label}
</SelectItem>
))}
</SelectContent>
</Select>
)}
</div>
);
}
// ---------------------------------------------------------------------------
// Sortable effect item
// ---------------------------------------------------------------------------
interface SortableEffectItemProps {
id: string;
effect: EffectConfig;
index: number;
effectDef?: AvailableEffect;
isExpanded: boolean;
onToggleExpand: () => void;
onRemove: () => void;
onToggleEnabled: () => void;
onUpdateParam: (paramName: string, paramValue: number) => void;
}
function SortableEffectItem({
id,
effect,
effectDef,
isExpanded,
onToggleExpand,
onRemove,
onToggleEnabled,
onUpdateParam,
}: SortableEffectItemProps) {
const { attributes, listeners, setNodeRef, transform, transition, isDragging } = useSortable({
id,
});
const style = {
transform: CSS.Transform.toString(transform),
transition,
zIndex: isDragging ? 10 : undefined,
};
const label = effectDef?.label ?? effect.type;
return (
<div
ref={setNodeRef}
style={style}
className={cn(
'rounded-md border',
effect.enabled ? 'border-border bg-card' : 'border-border/50 bg-muted/30',
isDragging && 'opacity-80 shadow-lg',
)}
>
{/* Header */}
<div className="flex items-center gap-1 px-2 py-1.5">
<button
type="button"
className="p-0.5 text-muted-foreground hover:text-foreground"
onClick={onToggleExpand}
>
{isExpanded ? (
<ChevronDown className="h-3.5 w-3.5" />
) : (
<ChevronRight className="h-3.5 w-3.5" />
)}
</button>
<button
type="button"
className="p-0.5 text-muted-foreground/50 hover:text-muted-foreground cursor-grab active:cursor-grabbing touch-none"
{...attributes}
{...listeners}
>
<GripVertical className="h-3.5 w-3.5" />
</button>
<span
className={cn('flex-1 text-xs font-medium', !effect.enabled && 'text-muted-foreground')}
>
{label}
</span>
<button
type="button"
className={cn(
'p-0.5 transition-colors',
effect.enabled ? 'text-primary' : 'text-muted-foreground hover:text-foreground',
)}
onClick={onToggleEnabled}
title={effect.enabled ? 'Disable' : 'Enable'}
>
<Power className="h-3.5 w-3.5" />
</button>
<button
type="button"
className="p-0.5 text-muted-foreground hover:text-destructive"
onClick={onRemove}
title="Remove"
>
<Trash2 className="h-3.5 w-3.5" />
</button>
</div>
{/* Params */}
{isExpanded && effectDef && (
<div className="space-y-3 border-t px-3 py-2.5">
{Object.entries(effectDef.params).map(([paramName, paramDef]) => {
const currentValue = effect.params[paramName] ?? paramDef.default;
return (
<div key={paramName} className="space-y-1">
<div className="flex items-center justify-between">
<Label className="text-[11px] text-muted-foreground">
{paramDef.description}
</Label>
<span className="text-[11px] font-mono tabular-nums text-foreground">
{currentValue.toFixed(
paramDef.step < 1 ? Math.max(1, -Math.floor(Math.log10(paramDef.step))) : 0,
)}
</span>
</div>
<Slider
min={paramDef.min}
max={paramDef.max}
step={paramDef.step}
value={[currentValue]}
onValueChange={([v]) => onUpdateParam(paramName, v)}
/>
</div>
);
})}
</div>
)}
</div>
);
}
@@ -0,0 +1,103 @@
import { ChevronDown, Search } from 'lucide-react';
import { useMemo, useState } from 'react';
import { Button } from '@/components/ui/button';
import { Input } from '@/components/ui/input';
import { Popover, PopoverContent, PopoverTrigger } from '@/components/ui/popover';
import type { HistoryResponse } from '@/lib/api/types';
import { useHistory } from '@/lib/hooks/useHistory';
import { cn } from '@/lib/utils/cn';
interface GenerationPickerProps {
selectedId: string | null;
onSelect: (generation: HistoryResponse) => void;
className?: string;
}
export function GenerationPicker({ selectedId, onSelect, className }: GenerationPickerProps) {
const [open, setOpen] = useState(false);
const [searchQuery, setSearchQuery] = useState('');
const { data: historyData } = useHistory({ limit: 50 });
const completedGenerations = useMemo(() => {
if (!historyData?.items) return [];
return historyData.items.filter((gen) => gen.status === 'completed');
}, [historyData]);
const filtered = useMemo(() => {
if (!searchQuery) return completedGenerations;
const q = searchQuery.toLowerCase();
return completedGenerations.filter(
(gen) => gen.text.toLowerCase().includes(q) || gen.profile_name.toLowerCase().includes(q),
);
}, [completedGenerations, searchQuery]);
const selectedGeneration = completedGenerations.find((g) => g.id === selectedId);
return (
<Popover open={open} onOpenChange={setOpen}>
<PopoverTrigger asChild>
<Button
variant="outline"
size="sm"
className={cn('h-8 justify-between gap-2 text-xs font-normal', className)}
>
{selectedGeneration ? (
<span className="truncate">
<span className="font-medium">{selectedGeneration.profile_name}</span>
<span className="text-muted-foreground ml-1.5">
{selectedGeneration.text.length > 30
? `${selectedGeneration.text.substring(0, 30)}...`
: selectedGeneration.text}
</span>
</span>
) : (
<span className="text-muted-foreground">Select a generation...</span>
)}
<ChevronDown className="h-3.5 w-3.5 shrink-0 opacity-50" />
</Button>
</PopoverTrigger>
<PopoverContent className="w-80 p-0" align="start">
<div className="p-2 border-b">
<div className="relative">
<Search className="absolute left-2 top-1/2 -translate-y-1/2 h-3.5 w-3.5 text-muted-foreground" />
<Input
placeholder="Search by voice or text..."
value={searchQuery}
onChange={(e) => setSearchQuery(e.target.value)}
className="h-8 pl-7 text-xs"
/>
</div>
</div>
<div className="max-h-60 overflow-y-auto">
{filtered.length === 0 ? (
<div className="p-4 text-center text-xs text-muted-foreground">
No generations found
</div>
) : (
filtered.map((gen) => (
<button
key={gen.id}
type="button"
className={cn(
'w-full text-left px-3 py-2 hover:bg-muted/50 transition-colors border-b border-border/30 last:border-0',
gen.id === selectedId && 'bg-accent/10',
)}
onClick={() => {
onSelect(gen);
setOpen(false);
setSearchQuery('');
}}
>
<div className="font-medium text-sm">{gen.profile_name}</div>
<div className="text-xs text-muted-foreground truncate">
{gen.text.length > 60 ? `${gen.text.substring(0, 60)}...` : gen.text}
</div>
</button>
))
)}
</div>
</PopoverContent>
</Popover>
);
}
@@ -0,0 +1,422 @@
import { useQuery, useQueryClient } from '@tanstack/react-query';
import { Loader2, Play, Save, Trash2, Wand2 } from 'lucide-react';
import { useEffect, useRef, useState } from 'react';
import { EffectsChainEditor } from '@/components/Effects/EffectsChainEditor';
import { GenerationPicker } from '@/components/Effects/GenerationPicker';
import { Button } from '@/components/ui/button';
import {
Dialog,
DialogContent,
DialogDescription,
DialogFooter,
DialogHeader,
DialogTitle,
} from '@/components/ui/dialog';
import { Input } from '@/components/ui/input';
import { Label } from '@/components/ui/label';
import { Separator } from '@/components/ui/separator';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import type { HistoryResponse } from '@/lib/api/types';
import { useHistory } from '@/lib/hooks/useHistory';
import { useEffectsStore } from '@/stores/effectsStore';
import { usePlayerStore } from '@/stores/playerStore';
export function EffectsDetail() {
const selectedPresetId = useEffectsStore((s) => s.selectedPresetId);
const isCreatingNew = useEffectsStore((s) => s.isCreatingNew);
const workingChain = useEffectsStore((s) => s.workingChain);
const setWorkingChain = useEffectsStore((s) => s.setWorkingChain);
const setSelectedPresetId = useEffectsStore((s) => s.setSelectedPresetId);
const setIsCreatingNew = useEffectsStore((s) => s.setIsCreatingNew);
const [name, setName] = useState('');
const [description, setDescription] = useState('');
const [saving, setSaving] = useState(false);
const [deleting, setDeleting] = useState(false);
// "Save as Custom" dialog state
const [saveAsDialogOpen, setSaveAsDialogOpen] = useState(false);
const [saveAsName, setSaveAsName] = useState('');
const [saveAsDescription, setSaveAsDescription] = useState('');
// Preview state
const [previewGenId, setPreviewGenId] = useState<string | null>(null);
const [previewLoading, setPreviewLoading] = useState(false);
const blobUrlRef = useRef<string | null>(null);
const setAudioWithAutoPlay = usePlayerStore((s) => s.setAudioWithAutoPlay);
const { toast } = useToast();
const queryClient = useQueryClient();
// Auto-select the most recent generation as preview source
const { data: historyData } = useHistory({ limit: 1 });
useEffect(() => {
if (!previewGenId && historyData?.items?.length) {
const first = historyData.items.find((g) => g.status === 'completed');
if (first) setPreviewGenId(first.id);
}
}, [historyData, previewGenId]);
const { data: preset } = useQuery({
queryKey: ['effect-preset', selectedPresetId],
queryFn: () =>
selectedPresetId
? apiClient
.listEffectPresets()
.then((all) => all.find((p) => p.id === selectedPresetId) ?? null)
: null,
enabled: !!selectedPresetId,
staleTime: 30_000,
});
// Sync name/description when selecting a preset
useEffect(() => {
if (preset) {
setName(preset.name);
setDescription(preset.description ?? '');
} else if (isCreatingNew) {
setName('');
setDescription('');
}
}, [preset, isCreatingNew]);
// Cleanup blob URL on unmount
useEffect(() => {
return () => {
if (blobUrlRef.current) {
URL.revokeObjectURL(blobUrlRef.current);
blobUrlRef.current = null;
}
};
}, []);
const isEditing = !!selectedPresetId || isCreatingNew;
const isBuiltIn = preset?.is_builtin ?? false;
async function handlePreview() {
if (!previewGenId || workingChain.length === 0) return;
setPreviewLoading(true);
try {
const blob = await apiClient.previewEffects(previewGenId, workingChain);
// Revoke old blob URL
if (blobUrlRef.current) {
URL.revokeObjectURL(blobUrlRef.current);
}
const url = URL.createObjectURL(blob);
blobUrlRef.current = url;
// Play through the main audio player
setAudioWithAutoPlay(url, `preview-${Date.now()}`, null, 'Effects Preview');
} catch (error) {
toast({
title: 'Preview failed',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setPreviewLoading(false);
}
}
function handleSelectGeneration(gen: HistoryResponse) {
setPreviewGenId(gen.id);
}
async function handleSaveNew() {
if (!name.trim()) {
toast({ title: 'Name required', variant: 'destructive' });
return;
}
setSaving(true);
try {
const created = await apiClient.createEffectPreset({
name: name.trim(),
description: description.trim() || undefined,
effects_chain: workingChain,
});
queryClient.invalidateQueries({ queryKey: ['effect-presets'] });
setIsCreatingNew(false);
setSelectedPresetId(created.id);
toast({ title: 'Preset saved', description: `"${created.name}" has been created.` });
} catch (error) {
toast({
title: 'Failed to save',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setSaving(false);
}
}
async function handleSaveExisting() {
if (!selectedPresetId || !name.trim()) return;
setSaving(true);
try {
await apiClient.updateEffectPreset(selectedPresetId, {
name: name.trim(),
description: description.trim() || undefined,
effects_chain: workingChain,
});
queryClient.invalidateQueries({ queryKey: ['effect-presets'] });
queryClient.invalidateQueries({ queryKey: ['effect-preset', selectedPresetId] });
toast({ title: 'Preset updated' });
} catch (error) {
toast({
title: 'Failed to save',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setSaving(false);
}
}
function handleSaveAsNew() {
// Open the dialog with a suggested name based on the current preset
setSaveAsName(`${name} (Copy)`);
setSaveAsDescription(description);
setSaveAsDialogOpen(true);
}
async function handleSaveAsConfirm() {
if (!saveAsName.trim()) {
toast({ title: 'Name required', variant: 'destructive' });
return;
}
setSaving(true);
try {
const created = await apiClient.createEffectPreset({
name: saveAsName.trim(),
description: saveAsDescription.trim() || undefined,
effects_chain: workingChain,
});
queryClient.invalidateQueries({ queryKey: ['effect-presets'] });
setSaveAsDialogOpen(false);
setSelectedPresetId(created.id);
toast({ title: 'Preset saved', description: `"${created.name}" has been created.` });
} catch (error) {
toast({
title: 'Failed to save',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setSaving(false);
}
}
async function handleDelete() {
if (!selectedPresetId) return;
setDeleting(true);
try {
await apiClient.deleteEffectPreset(selectedPresetId);
queryClient.invalidateQueries({ queryKey: ['effect-presets'] });
setSelectedPresetId(null);
setWorkingChain([]);
toast({ title: 'Preset deleted' });
} catch (error) {
toast({
title: 'Failed to delete',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setDeleting(false);
}
}
if (!isEditing) {
return (
<div className="flex-1 flex items-center justify-center text-muted-foreground">
<div className="text-center space-y-2">
<Wand2 className="h-10 w-10 mx-auto opacity-30" />
<p className="text-sm">Select a preset or create a new one</p>
</div>
</div>
);
}
return (
<div className="flex flex-col h-full min-h-0">
{/* Header */}
<div className="flex items-center justify-between mb-4">
<h2 className="text-lg font-semibold">
{isCreatingNew ? 'New Preset' : isBuiltIn ? preset?.name : 'Edit Preset'}
</h2>
<div className="flex items-center gap-2">
{!isBuiltIn && !isCreatingNew && (
<>
<Button
variant="ghost"
size="sm"
className="h-8 text-destructive hover:text-destructive gap-1.5"
onClick={handleDelete}
disabled={deleting}
>
<Trash2 className="h-3.5 w-3.5" />
{deleting ? 'Deleting...' : 'Delete'}
</Button>
<Button
size="sm"
className="h-8 gap-1.5"
onClick={handleSaveExisting}
disabled={saving || workingChain.length === 0}
>
<Save className="h-3.5 w-3.5" />
{saving ? 'Saving...' : 'Save'}
</Button>
</>
)}
{isCreatingNew && (
<Button
size="sm"
className="h-8 gap-1.5"
onClick={handleSaveNew}
disabled={saving || workingChain.length === 0}
>
<Save className="h-3.5 w-3.5" />
{saving ? 'Saving...' : 'Save Preset'}
</Button>
)}
{isBuiltIn && (
<Button
size="sm"
variant="outline"
className="h-8 gap-1.5"
onClick={handleSaveAsNew}
disabled={saving}
>
<Save className="h-3.5 w-3.5" />
{saving ? 'Saving...' : 'Save as Custom'}
</Button>
)}
</div>
</div>
{/* Scrollable content */}
<div className="flex-1 min-h-0 overflow-y-auto space-y-5 pr-1">
{/* Name & description */}
{(isCreatingNew || !isBuiltIn) && (
<div className="space-y-3">
<div className="space-y-1.5">
<Label className="text-xs">Name</Label>
<Input
value={name}
onChange={(e) => setName(e.target.value)}
placeholder="My preset..."
className="h-9"
/>
</div>
<div className="space-y-1.5">
<Label className="text-xs">Description</Label>
<Textarea
value={description}
onChange={(e) => setDescription(e.target.value)}
placeholder="Describe what this preset does..."
className="min-h-[60px] resize-none"
/>
</div>
</div>
)}
{/* Built-in description (read-only) */}
{isBuiltIn && preset?.description && (
<p className="text-sm text-muted-foreground">{preset.description}</p>
)}
{/* Effects chain editor */}
<EffectsChainEditor value={workingChain} onChange={setWorkingChain} showPresets={false} />
<Separator />
{/* Preview section */}
<div className="space-y-3">
<Label className="text-xs">Preview</Label>
<div className="flex items-center gap-2">
<GenerationPicker
selectedId={previewGenId}
onSelect={handleSelectGeneration}
className="flex-1"
/>
<Button
variant="outline"
size="sm"
className="h-8 gap-1.5 shrink-0"
onClick={handlePreview}
disabled={!previewGenId || workingChain.length === 0 || previewLoading}
>
{previewLoading ? (
<>
<Loader2 className="h-3.5 w-3.5 animate-spin" />
Processing...
</>
) : (
<>
<Play className="h-3.5 w-3.5" />
Preview
</>
)}
</Button>
</div>
<p className="text-[11px] text-muted-foreground">
Preview applies effects to the clean version without saving.
</p>
</div>
</div>
{/* Save as Custom dialog */}
<Dialog open={saveAsDialogOpen} onOpenChange={setSaveAsDialogOpen}>
<DialogContent className="sm:max-w-md">
<DialogHeader>
<DialogTitle>Save as Custom Preset</DialogTitle>
<DialogDescription>
Create a new custom preset based on the current effects chain.
</DialogDescription>
</DialogHeader>
<div className="space-y-3 py-2">
<div className="space-y-1.5">
<Label className="text-xs">Name</Label>
<Input
value={saveAsName}
onChange={(e) => setSaveAsName(e.target.value)}
placeholder="My preset..."
className="h-9"
autoFocus
onKeyDown={(e) => {
if (e.key === 'Enter' && saveAsName.trim()) {
handleSaveAsConfirm();
}
}}
/>
</div>
<div className="space-y-1.5">
<Label className="text-xs">Description</Label>
<Textarea
value={saveAsDescription}
onChange={(e) => setSaveAsDescription(e.target.value)}
placeholder="Describe what this preset does..."
className="min-h-[60px] resize-none"
/>
</div>
</div>
<DialogFooter>
<Button variant="outline" onClick={() => setSaveAsDialogOpen(false)} disabled={saving}>
Cancel
</Button>
<Button onClick={handleSaveAsConfirm} disabled={saving || !saveAsName.trim()}>
<Save className="h-3.5 w-3.5 mr-1.5" />
{saving ? 'Saving...' : 'Save'}
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
</div>
);
}
@@ -0,0 +1,165 @@
import { useQuery } from '@tanstack/react-query';
import { Loader2, Plus, Sparkles, Wand2 } from 'lucide-react';
import { Button } from '@/components/ui/button';
import { apiClient } from '@/lib/api/client';
import type { EffectPresetResponse } from '@/lib/api/types';
import { cn } from '@/lib/utils/cn';
import { useEffectsStore } from '@/stores/effectsStore';
export function EffectsList() {
const selectedPresetId = useEffectsStore((s) => s.selectedPresetId);
const setSelectedPresetId = useEffectsStore((s) => s.setSelectedPresetId);
const setWorkingChain = useEffectsStore((s) => s.setWorkingChain);
const setIsCreatingNew = useEffectsStore((s) => s.setIsCreatingNew);
const isCreatingNew = useEffectsStore((s) => s.isCreatingNew);
const { data: presets, isLoading } = useQuery({
queryKey: ['effect-presets'],
queryFn: () => apiClient.listEffectPresets(),
staleTime: 30_000,
});
const builtIn = presets?.filter((p) => p.is_builtin) ?? [];
const userPresets = presets?.filter((p) => !p.is_builtin) ?? [];
function handleSelect(preset: EffectPresetResponse) {
setSelectedPresetId(preset.id);
setWorkingChain(preset.effects_chain);
}
function handleCreateNew() {
setIsCreatingNew(true);
setWorkingChain([]);
}
if (isLoading) {
return (
<div className="flex items-center justify-center h-full">
<Loader2 className="h-6 w-6 animate-spin text-muted-foreground" />
</div>
);
}
return (
<div className="flex flex-col h-full min-h-0">
{/* Header */}
<div className="flex items-center justify-between mb-4">
<h2 className="text-lg font-semibold">Effects</h2>
<Button variant="outline" size="sm" className="h-8 gap-1.5" onClick={handleCreateNew}>
<Plus className="h-3.5 w-3.5" />
New Preset
</Button>
</div>
{/* Scrollable list */}
<div className="flex-1 min-h-0 overflow-y-auto space-y-4">
{/* Built-in presets */}
{builtIn.length > 0 && (
<div>
<div className="text-[11px] text-muted-foreground font-medium uppercase tracking-wider mb-2 px-1">
Built-in
</div>
<div className="space-y-1.5">
{builtIn.map((preset) => (
<PresetCard
key={preset.id}
preset={preset}
isSelected={selectedPresetId === preset.id && !isCreatingNew}
onSelect={() => handleSelect(preset)}
/>
))}
</div>
</div>
)}
{/* User presets */}
{userPresets.length > 0 && (
<div>
<div className="text-[11px] text-muted-foreground font-medium uppercase tracking-wider mb-2 px-1">
Custom
</div>
<div className="space-y-1.5">
{userPresets.map((preset) => (
<PresetCard
key={preset.id}
preset={preset}
isSelected={selectedPresetId === preset.id && !isCreatingNew}
onSelect={() => handleSelect(preset)}
/>
))}
</div>
</div>
)}
{/* New preset placeholder */}
{isCreatingNew && (
<div>
<div className="text-[11px] text-muted-foreground font-medium uppercase tracking-wider mb-2 px-1">
New
</div>
<div className="rounded-xl border-2 border-accent/40 bg-accent/5 p-3">
<div className="flex items-center gap-2">
<Sparkles className="h-4 w-4 text-accent" />
<span className="text-sm font-medium">Unsaved Preset</span>
</div>
<p className="text-xs text-muted-foreground mt-1">
Configure effects in the panel on the right.
</p>
</div>
</div>
)}
</div>
</div>
);
}
function PresetCard({
preset,
isSelected,
onSelect,
}: {
preset: EffectPresetResponse;
isSelected: boolean;
onSelect: () => void;
}) {
const effectCount = preset.effects_chain.length;
return (
<button
type="button"
className={cn(
'w-full text-left rounded-xl border p-3 h-[88px] transition-all duration-150',
isSelected
? 'border-accent/50 bg-accent/10'
: 'border-border bg-card hover:bg-muted/50 hover:border-border',
)}
onClick={onSelect}
>
<div className="flex items-center gap-2">
<Wand2
className={cn('h-4 w-4 shrink-0', isSelected ? 'text-accent' : 'text-muted-foreground')}
/>
<span className="text-sm font-medium truncate">{preset.name}</span>
{preset.is_builtin && (
<span className="text-[10px] bg-muted text-muted-foreground px-1.5 py-0.5 rounded-full shrink-0">
built-in
</span>
)}
</div>
<p className="text-xs text-muted-foreground mt-1 line-clamp-1 pl-6">
{preset.description || 'No description'}
</p>
<div className="flex items-center gap-2 mt-1.5 pl-6">
<span className="text-[10px] text-muted-foreground">
{effectCount} effect{effectCount !== 1 ? 's' : ''}
</span>
<span className="text-[10px] text-muted-foreground/50">
{preset.effects_chain
.filter((e) => e.enabled)
.map((e) => e.type)
.join(' → ')}
</span>
</div>
</button>
);
}
@@ -0,0 +1,20 @@
import { EffectsDetail } from './EffectsDetail';
import { EffectsList } from './EffectsList';
export function EffectsTab() {
return (
<div className="flex flex-col h-full min-h-0 overflow-hidden">
<div className="flex-1 min-h-0 flex gap-6 overflow-hidden">
{/* Left - Presets list */}
<div className="w-full max-w-[360px] shrink-0 flex flex-col min-h-0">
<EffectsList />
</div>
{/* Right - Detail / editor */}
<div className="flex-1 min-h-0 flex flex-col">
<EffectsDetail />
</div>
</div>
</div>
);
}
@@ -0,0 +1,170 @@
import { useEffect } from 'react';
import type { UseFormReturn } from 'react-hook-form';
import { FormControl } from '@/components/ui/form';
import {
Select,
SelectContent,
SelectItem,
SelectTrigger,
SelectValue,
} from '@/components/ui/select';
import type { VoiceProfileResponse } from '@/lib/api/types';
import { getLanguageOptionsForEngine } from '@/lib/constants/languages';
import type { GenerationFormValues } from '@/lib/hooks/useGenerationForm';
/**
* Engine/model options and their display metadata.
* Adding a new engine means adding one entry here.
*/
const ENGINE_OPTIONS = [
{ value: 'qwen:1.7B', label: 'Qwen3-TTS 1.7B', engine: 'qwen' },
{ value: 'qwen:0.6B', label: 'Qwen3-TTS 0.6B', engine: 'qwen' },
{ value: 'qwen_custom_voice:1.7B', label: 'Qwen CustomVoice 1.7B', engine: 'qwen_custom_voice' },
{ value: 'qwen_custom_voice:0.6B', label: 'Qwen CustomVoice 0.6B', engine: 'qwen_custom_voice' },
{ value: 'luxtts', label: 'LuxTTS', engine: 'luxtts' },
{ value: 'chatterbox', label: 'Chatterbox', engine: 'chatterbox' },
{ value: 'chatterbox_turbo', label: 'Chatterbox Turbo', engine: 'chatterbox_turbo' },
{ value: 'tada:1B', label: 'TADA 1B', engine: 'tada' },
{ value: 'tada:3B', label: 'TADA 3B Multilingual', engine: 'tada' },
{ value: 'kokoro', label: 'Kokoro 82M', engine: 'kokoro' },
] as const;
const ENGINE_DESCRIPTIONS: Record<string, string> = {
qwen: 'Multi-language, two sizes',
qwen_custom_voice: '9 preset voices, instruct control',
luxtts: 'Fast, English-focused',
chatterbox: '23 languages, incl. Hebrew',
chatterbox_turbo: 'English, [laugh] [cough] tags',
tada: 'HumeAI, 700s+ coherent audio',
kokoro: '82M params, CPU realtime, 8 langs',
};
/** Engines that only support English and should force language to 'en' on select. */
const ENGLISH_ONLY_ENGINES = new Set(['luxtts', 'chatterbox_turbo']);
/** Engines that support cloned (reference audio) profiles. */
const CLONING_ENGINES = new Set(['qwen', 'luxtts', 'chatterbox', 'chatterbox_turbo', 'tada']);
function getAvailableOptions(selectedProfile?: VoiceProfileResponse | null) {
if (!selectedProfile) return ENGINE_OPTIONS;
return ENGINE_OPTIONS.filter((opt) => isProfileCompatibleWithEngine(selectedProfile, opt.engine));
}
function getSelectValue(engine: string, modelSize?: string): string {
if (engine === 'qwen') return `qwen:${modelSize || '1.7B'}`;
if (engine === 'qwen_custom_voice') return `qwen_custom_voice:${modelSize || '1.7B'}`;
if (engine === 'tada') return `tada:${modelSize || '1B'}`;
return engine;
}
export function applyEngineSelection(form: UseFormReturn<GenerationFormValues>, value: string) {
if (value.startsWith('qwen_custom_voice:')) {
const [, modelSize] = value.split(':');
form.setValue('engine', 'qwen_custom_voice');
form.setValue('modelSize', modelSize as '1.7B' | '0.6B');
const currentLang = form.getValues('language');
const available = getLanguageOptionsForEngine('qwen_custom_voice');
if (!available.some((l) => l.value === currentLang)) {
form.setValue('language', available[0]?.value ?? 'en');
}
} else if (value.startsWith('qwen:')) {
const [, modelSize] = value.split(':');
form.setValue('engine', 'qwen');
form.setValue('modelSize', modelSize as '1.7B' | '0.6B');
// Validate language is supported by Qwen
const currentLang = form.getValues('language');
const available = getLanguageOptionsForEngine('qwen');
if (!available.some((l) => l.value === currentLang)) {
form.setValue('language', available[0]?.value ?? 'en');
}
} else if (value.startsWith('tada:')) {
const [, modelSize] = value.split(':');
form.setValue('engine', 'tada');
form.setValue('modelSize', modelSize as '1B' | '3B');
// TADA 1B is English-only; 3B is multilingual
if (modelSize === '1B') {
form.setValue('language', 'en');
} else {
const currentLang = form.getValues('language');
const available = getLanguageOptionsForEngine('tada');
if (!available.some((l) => l.value === currentLang)) {
form.setValue('language', available[0]?.value ?? 'en');
}
}
} else {
form.setValue('engine', value as GenerationFormValues['engine']);
form.setValue('modelSize', undefined as unknown as '1.7B' | '0.6B');
if (ENGLISH_ONLY_ENGINES.has(value)) {
form.setValue('language', 'en');
} else {
// If current language isn't supported by the new engine, reset to first available
const currentLang = form.getValues('language');
const available = getLanguageOptionsForEngine(value);
if (!available.some((l) => l.value === currentLang)) {
form.setValue('language', available[0]?.value ?? 'en');
}
}
}
}
interface EngineModelSelectorProps {
form: UseFormReturn<GenerationFormValues>;
compact?: boolean;
selectedProfile?: VoiceProfileResponse | null;
}
export function EngineModelSelector({ form, compact, selectedProfile }: EngineModelSelectorProps) {
const engine = form.watch('engine') || 'qwen';
const modelSize = form.watch('modelSize');
const selectValue = getSelectValue(engine, modelSize);
const availableOptions = getAvailableOptions(selectedProfile);
const currentEngineAvailable = availableOptions.some((opt) => opt.value === selectValue);
useEffect(() => {
if (!currentEngineAvailable && availableOptions.length > 0) {
applyEngineSelection(form, availableOptions[0].value);
}
}, [availableOptions, currentEngineAvailable, form]);
const itemClass = compact ? 'text-xs text-muted-foreground' : undefined;
const triggerClass = compact
? 'h-8 text-xs bg-card border-border rounded-full hover:bg-background/50 transition-all'
: undefined;
return (
<Select value={selectValue} onValueChange={(v) => applyEngineSelection(form, v)}>
<FormControl>
<SelectTrigger className={triggerClass}>
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
{availableOptions.map((opt) => (
<SelectItem key={opt.value} value={opt.value} className={itemClass}>
{opt.label}
</SelectItem>
))}
</SelectContent>
</Select>
);
}
/** Returns a human-readable description for the currently selected engine. */
export function getEngineDescription(engine: string): string {
return ENGINE_DESCRIPTIONS[engine] ?? '';
}
/**
* Check if a profile is compatible with the currently selected engine.
* Useful for UI hints.
*/
export function isProfileCompatibleWithEngine(
profile: VoiceProfileResponse,
engine: string,
): boolean {
const voiceType = profile.voice_type || 'cloned';
if (voiceType === 'preset') return profile.preset_engine === engine;
if (voiceType === 'cloned') return CLONING_ENGINES.has(engine);
return true; // designed — future
}
@@ -1,6 +1,7 @@
import { useQuery } from '@tanstack/react-query';
import { useMatchRoute } from '@tanstack/react-router';
import { AnimatePresence, motion } from 'framer-motion';
import { Loader2, MessageSquare, Sparkles } from 'lucide-react';
import { Loader2, SlidersHorizontal, Sparkles } from 'lucide-react';
import { useEffect, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import { Form, FormControl, FormField, FormItem, FormMessage } from '@/components/ui/form';
@@ -12,14 +13,17 @@ import {
SelectValue,
} from '@/components/ui/select';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
import { LANGUAGE_OPTIONS } from '@/lib/constants/languages';
import { apiClient } from '@/lib/api/client';
import { getLanguageOptionsForEngine, type LanguageCode } from '@/lib/constants/languages';
import { useGenerationForm } from '@/lib/hooks/useGenerationForm';
import { useProfile, useProfiles } from '@/lib/hooks/useProfiles';
import { useAddStoryItem, useStory } from '@/lib/hooks/useStories';
import { useStory } from '@/lib/hooks/useStories';
import { cn } from '@/lib/utils/cn';
import { useGenerationStore } from '@/stores/generationStore';
import { useStoryStore } from '@/stores/storyStore';
import { useUIStore } from '@/stores/uiStore';
import { EngineModelSelector } from './EngineModelSelector';
import { ParalinguisticInput } from './ParalinguisticInput';
interface FloatingGenerateBoxProps {
isPlayerOpen?: boolean;
@@ -32,10 +36,12 @@ export function FloatingGenerateBox({
}: FloatingGenerateBoxProps) {
const selectedProfileId = useUIStore((state) => state.selectedProfileId);
const setSelectedProfileId = useUIStore((state) => state.setSelectedProfileId);
const setSelectedEngine = useUIStore((state) => state.setSelectedEngine);
const { data: selectedProfile } = useProfile(selectedProfileId || '');
const { data: profiles } = useProfiles();
const [isExpanded, setIsExpanded] = useState(false);
const [isInstructMode, setIsInstructMode] = useState(false);
const [isInstructExpanded, setIsInstructExpanded] = useState(false);
const [selectedPresetId, setSelectedPresetId] = useState<string | null>(null);
const containerRef = useRef<HTMLDivElement>(null);
const textareaRef = useRef<HTMLTextAreaElement | null>(null);
const matchRoute = useMatchRoute();
@@ -43,8 +49,13 @@ export function FloatingGenerateBox({
const selectedStoryId = useStoryStore((state) => state.selectedStoryId);
const trackEditorHeight = useStoryStore((state) => state.trackEditorHeight);
const { data: currentStory } = useStory(selectedStoryId);
const addStoryItem = useAddStoryItem();
const { toast } = useToast();
const addPendingStoryAdd = useGenerationStore((s) => s.addPendingStoryAdd);
// Fetch effect presets for the dropdown
const { data: effectPresets } = useQuery({
queryKey: ['effectPresets'],
queryFn: () => apiClient.listEffectPresets(),
});
// Calculate if track editor is visible (on stories route with items)
const hasTrackEditor = isStoriesRoute && currentStory && currentStory.items.length > 0;
@@ -52,27 +63,21 @@ export function FloatingGenerateBox({
const { form, handleSubmit, isPending } = useGenerationForm({
onSuccess: async (generationId) => {
setIsExpanded(false);
// If on stories route and a story is selected, add generation to story
// Defer the story add until TTS completes -- useGenerationProgress handles it
if (isStoriesRoute && selectedStoryId && generationId) {
try {
await addStoryItem.mutateAsync({
storyId: selectedStoryId,
data: { generation_id: generationId },
});
toast({
title: 'Added to story',
description: `Generation added to "${currentStory?.name || 'story'}"`,
});
} catch (error) {
toast({
title: 'Failed to add to story',
description:
error instanceof Error ? error.message : 'Could not add generation to story',
variant: 'destructive',
});
}
addPendingStoryAdd(generationId, selectedStoryId);
}
},
getEffectsChain: () => {
if (!selectedPresetId) return undefined;
// Profile's own effects chain (no matching preset)
if (selectedPresetId === '_profile') {
return selectedProfile?.effects_chain ?? undefined;
}
if (!effectPresets) return undefined;
const preset = effectPresets.find((p) => p.id === selectedPresetId);
return preset?.effects_chain;
},
});
// Click away handler to collapse the box
@@ -112,6 +117,64 @@ export function FloatingGenerateBox({
}
}, [selectedProfileId, profiles, setSelectedProfileId]);
// Sync engine selection to global store so ProfileList can filter
const watchedEngine = form.watch('engine');
useEffect(() => {
if (watchedEngine) {
setSelectedEngine(watchedEngine);
}
}, [watchedEngine, setSelectedEngine]);
// Sync generation form language, engine, and effects with selected profile
type EngineValue =
| 'qwen'
| 'luxtts'
| 'chatterbox'
| 'chatterbox_turbo'
| 'tada'
| 'kokoro'
| 'qwen_custom_voice';
useEffect(() => {
if (selectedProfile?.language) {
form.setValue('language', selectedProfile.language as LanguageCode);
}
// Auto-switch engine to match the profile
const engine = selectedProfile?.default_engine ?? selectedProfile?.preset_engine;
if (engine) {
form.setValue('engine', engine as EngineValue);
} else if (selectedProfile && selectedProfile.voice_type !== 'preset') {
// Cloned/designed profile with no default — ensure a compatible (non-preset) engine
const currentEngine = form.getValues('engine');
const presetEngines = new Set(['kokoro', 'qwen_custom_voice']);
if (currentEngine && presetEngines.has(currentEngine)) {
form.setValue('engine', 'qwen');
}
}
// Pre-fill effects from profile defaults
if (
selectedProfile?.effects_chain &&
selectedProfile.effects_chain.length > 0 &&
effectPresets
) {
// Try to match against a known preset
const profileChainJson = JSON.stringify(selectedProfile.effects_chain);
const matchingPreset = effectPresets.find(
(p) => JSON.stringify(p.effects_chain) === profileChainJson,
);
if (matchingPreset) {
setSelectedPresetId(matchingPreset.id);
} else {
// No matching preset — use special value to pass profile chain directly
setSelectedPresetId('_profile');
}
} else if (
selectedProfile &&
(!selectedProfile.effects_chain || selectedProfile.effects_chain.length === 0)
) {
setSelectedPresetId(null);
}
}, [selectedProfile, effectPresets, form]);
// Auto-resize textarea based on content (only when expanded)
useEffect(() => {
if (!isExpanded) {
@@ -174,7 +237,7 @@ export function FloatingGenerateBox({
isStoriesRoute
? // Position aligned with story list: after sidebar + padding, width 360px
'left-[calc(5rem+2rem)] w-[360px]'
: 'left-[calc(5rem+2rem)] w-[calc((100%-5rem-4rem)/2-1rem)]',
: 'left-[calc(5rem+2rem)] right-8 lg:right-auto lg:w-[calc((100%-5rem-4rem)/2-1rem)]',
)}
style={{
// On stories route: offset by track editor height when visible
@@ -187,39 +250,52 @@ export function FloatingGenerateBox({
}}
>
<motion.div
className="bg-background/30 backdrop-blur-2xl border border-accent/20 rounded-[2rem] shadow-2xl hover:bg-background/40 hover:border-accent/20 transition-all duration-300 overflow-hidden p-3"
className="bg-background/30 backdrop-blur-2xl border border-accent/20 rounded-[2rem] shadow-2xl hover:bg-background/40 hover:border-accent/20 transition-all duration-300 p-3"
transition={{ duration: 0.6, ease: 'easeInOut' }}
>
<Form {...form}>
<form onSubmit={form.handleSubmit(onSubmit)}>
<div className="flex gap-2">
<motion.div
className={cn('flex-1', isExpanded && 'mr-12')}
transition={{ duration: 0.3, ease: 'easeOut' }}
>
{/* Text field - hidden when in instruct mode */}
<div style={{ display: isInstructMode ? 'none' : 'block' }}>
<FormField
control={form.control}
name="text"
render={({ field }) => (
<FormItem>
<FormControl>
<motion.div
animate={{
height: isExpanded ? 'auto' : '32px',
}}
transition={{ duration: 0.15, ease: 'easeOut' }}
style={{ overflow: 'hidden' }}
>
<motion.div className="flex-1" transition={{ duration: 0.3, ease: 'easeOut' }}>
<FormField
control={form.control}
name="text"
render={({ field }) => (
<FormItem>
<FormControl>
<motion.div
animate={{
height: isExpanded ? 'auto' : '32px',
}}
transition={{ duration: 0.15, ease: 'easeOut' }}
style={{ overflow: 'hidden' }}
>
{form.watch('engine') === 'chatterbox_turbo' ? (
<ParalinguisticInput
value={field.value}
onChange={field.onChange}
placeholder={
isStoriesRoute && currentStory
? `Generate speech for "${currentStory.name}"... (type / for effects)`
: selectedProfile
? `Type / for effects like [laugh], [sigh]...`
: 'Select a voice profile above...'
}
className="px-3 py-2 resize-none bg-transparent border-none focus-visible:ring-0 focus-visible:ring-offset-0 focus:outline-none focus:ring-0 outline-none ring-0 rounded-2xl text-sm w-full"
style={{
minHeight: isExpanded ? '100px' : '32px',
maxHeight: '300px',
overflowY: 'auto',
}}
disabled={!selectedProfileId}
onClick={() => setIsExpanded(true)}
onFocus={() => setIsExpanded(true)}
/>
) : (
<Textarea
{...field}
ref={(node: HTMLTextAreaElement | null) => {
// Store ref for auto-resize (only for active field)
if (!isInstructMode) {
textareaRef.current = node;
}
// Forward ref to react-hook-form
textareaRef.current = node;
if (typeof field.ref === 'function') {
field.ref(node);
}
@@ -240,74 +316,48 @@ export function FloatingGenerateBox({
onClick={() => setIsExpanded(true)}
onFocus={() => setIsExpanded(true)}
/>
</motion.div>
</FormControl>
<FormMessage className="text-xs" />
</FormItem>
)}
/>
</div>
{/* Instruct field - hidden when in text mode */}
<div style={{ display: isInstructMode ? 'block' : 'none' }}>
<FormField
control={form.control}
name="instruct"
render={({ field }) => (
<FormItem>
<FormControl>
<motion.div
animate={{
height: isExpanded ? 'auto' : '32px',
}}
transition={{ duration: 0.15, ease: 'easeOut' }}
style={{ overflow: 'hidden' }}
>
<Textarea
{...field}
ref={(node: HTMLTextAreaElement | null) => {
// Store ref for auto-resize (only for active field)
if (isInstructMode) {
textareaRef.current = node;
}
// Forward ref to react-hook-form
if (typeof field.ref === 'function') {
field.ref(node);
}
}}
placeholder="Add delivery instructions..."
className="resize-none bg-transparent border-none focus-visible:ring-0 focus-visible:ring-offset-0 focus:outline-none focus:ring-0 outline-none ring-0 rounded-2xl text-sm placeholder:text-muted-foreground/60 w-full"
style={{
minHeight: isExpanded ? '100px' : '32px',
maxHeight: '300px',
}}
disabled={!selectedProfileId}
onClick={() => setIsExpanded(true)}
onFocus={() => setIsExpanded(true)}
/>
</motion.div>
</FormControl>
<FormMessage className="text-xs" />
</FormItem>
)}
/>
</div>
)}
</motion.div>
</FormControl>
<FormMessage className="text-xs" />
</FormItem>
)}
/>
</motion.div>
<div className="relative shrink-0">
<Button
type="submit"
disabled={isPending || !selectedProfileId}
className="h-10 w-10 rounded-full bg-accent hover:bg-accent/90 hover:scale-105 text-accent-foreground shadow-lg hover:shadow-accent/50 transition-all duration-200"
size="icon"
>
{isPending ? (
<Loader2 className="h-4 w-4 animate-spin" />
) : (
<Sparkles className="h-4 w-4" />
)}
</Button>
<div className="group relative">
<Button
type="submit"
disabled={isPending || !selectedProfileId}
className="h-10 w-10 rounded-full bg-accent hover:bg-accent/90 hover:scale-105 text-accent-foreground shadow-lg hover:shadow-accent/50 transition-all duration-200"
size="icon"
aria-label={
isPending
? 'Generating...'
: !selectedProfileId
? 'Select a voice profile first'
: 'Generate speech'
}
>
{isPending ? (
<Loader2 className="h-4 w-4 animate-spin" />
) : (
<Sparkles className="h-4 w-4" />
)}
</Button>
<span className="pointer-events-none absolute bottom-full left-1/2 -translate-x-1/2 mb-2 whitespace-nowrap rounded-md bg-popover px-3 py-1.5 text-xs text-popover-foreground border border-border opacity-0 transition-opacity group-hover:opacity-100 z-[9999]">
{isPending
? 'Generating...'
: !selectedProfileId
? 'Select a voice profile first'
: 'Generate speech'}
</span>
</div>
{/* Instruct toggle — only for Qwen CustomVoice, which actually honors the kwarg */}
<AnimatePresence>
{isExpanded && (
{isExpanded && form.watch('engine') === 'qwen_custom_voice' && (
<motion.div
initial={{ opacity: 0, scale: 0.8 }}
animate={{ opacity: 1, scale: 1 }}
@@ -315,26 +365,69 @@ export function FloatingGenerateBox({
transition={{ duration: 0.2 }}
className="absolute top-0 right-[calc(100%+0.5rem)]"
>
<Button
type="button"
variant="ghost"
size="icon"
onClick={() => setIsInstructMode(!isInstructMode)}
className={cn(
'h-10 w-10 rounded-full transition-all duration-200',
isInstructMode
? 'bg-accent text-accent-foreground border border-accent hover:bg-accent/90'
: 'bg-card border border-border hover:bg-background/50',
)}
>
<MessageSquare className="h-4 w-4" />
</Button>
<div className="group relative">
<Button
type="button"
variant="ghost"
size="icon"
onClick={() => setIsInstructExpanded((prev) => !prev)}
className={cn(
'h-10 w-10 rounded-full transition-all duration-200',
isInstructExpanded
? 'bg-accent text-accent-foreground border border-accent hover:bg-accent/90'
: 'bg-card border border-border hover:bg-background/50',
)}
aria-label={
isInstructExpanded
? 'Hide delivery instructions'
: 'Show delivery instructions'
}
aria-pressed={isInstructExpanded}
>
<SlidersHorizontal className="h-4 w-4" />
</Button>
<span className="pointer-events-none absolute bottom-full left-1/2 -translate-x-1/2 mb-2 whitespace-nowrap rounded-md bg-popover px-3 py-1.5 text-xs text-popover-foreground border border-border opacity-0 transition-opacity group-hover:opacity-100 z-[9999]">
Delivery instructions (tone, emotion, pace)
</span>
</div>
</motion.div>
)}
</AnimatePresence>
</div>
</div>
{/* Additive instruct textarea — shown below main text when toggle is on and engine supports it */}
<AnimatePresence>
{isInstructExpanded && form.watch('engine') === 'qwen_custom_voice' && (
<motion.div
initial={{ opacity: 0, height: 0 }}
animate={{ opacity: 1, height: 'auto' }}
exit={{ opacity: 0, height: 0 }}
transition={{ duration: 0.2, ease: 'easeOut' }}
className="overflow-hidden"
>
<FormField
control={form.control}
name="instruct"
render={({ field }) => (
<FormItem className="mt-2">
<FormControl>
<Textarea
{...field}
placeholder="Delivery instructions — e.g. Speak slowly with warmth, Authoritative and clear..."
className="resize-none bg-transparent border border-accent/20 focus-visible:ring-1 focus-visible:ring-accent/40 rounded-2xl text-sm placeholder:text-muted-foreground/60 w-full px-3 py-2"
style={{ minHeight: '60px', maxHeight: '160px' }}
maxLength={500}
/>
</FormControl>
<FormMessage className="text-xs" />
</FormItem>
)}
/>
</motion.div>
)}
</AnimatePresence>
<AnimatePresence>
<motion.div
initial={{ height: 0, opacity: 0 }}
@@ -367,51 +460,64 @@ export function FloatingGenerateBox({
<FormField
control={form.control}
name="language"
render={({ field }) => (
<FormItem className="flex-1 space-y-0">
<Select onValueChange={field.onChange} defaultValue={field.value}>
<FormControl>
<SelectTrigger className="h-8 text-xs bg-card border-border rounded-full hover:bg-background/50 transition-all">
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
{LANGUAGE_OPTIONS.map((lang) => (
<SelectItem key={lang.value} value={lang.value} className="text-xs">
{lang.label}
</SelectItem>
))}
</SelectContent>
</Select>
<FormMessage className="text-xs" />
</FormItem>
)}
render={({ field }) => {
const engineLangs = getLanguageOptionsForEngine(
form.watch('engine') || 'qwen',
);
return (
<FormItem className="flex-1 space-y-0">
<Select onValueChange={field.onChange} value={field.value}>
<FormControl>
<SelectTrigger className="h-8 text-xs bg-card border-border rounded-full hover:bg-background/50 transition-all">
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
{engineLangs.map((lang) => (
<SelectItem key={lang.value} value={lang.value} className="text-xs">
{lang.label}
</SelectItem>
))}
</SelectContent>
</Select>
<FormMessage className="text-xs" />
</FormItem>
);
}}
/>
<FormField
control={form.control}
name="modelSize"
render={({ field }) => (
<FormItem className="flex-1 space-y-0">
<Select onValueChange={field.onChange} defaultValue={field.value}>
<FormControl>
<SelectTrigger className="h-8 text-xs bg-card border-border rounded-full hover:bg-background/50 transition-all">
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
<SelectItem value="1.7B" className="text-xs text-muted-foreground">
Qwen3-TTS 1.7B
<FormItem className="flex-1 space-y-0">
<EngineModelSelector form={form} compact />
</FormItem>
<FormItem className="flex-1 space-y-0">
<Select
value={selectedPresetId || 'none'}
onValueChange={(value) =>
setSelectedPresetId(value === 'none' ? null : value)
}
>
<SelectTrigger className="h-8 text-xs bg-card border-border rounded-full hover:bg-background/50 transition-all">
<SelectValue placeholder="No effects" />
</SelectTrigger>
<SelectContent>
<SelectItem value="none" className="text-xs">
No effects
</SelectItem>
{selectedProfile?.effects_chain &&
selectedProfile.effects_chain.length > 0 && (
<SelectItem value="_profile" className="text-xs">
Profile default
</SelectItem>
<SelectItem value="0.6B" className="text-xs text-muted-foreground">
Qwen3-TTS 0.6B
</SelectItem>
</SelectContent>
</Select>
<FormMessage className="text-xs" />
</FormItem>
)}
/>
)}
{effectPresets?.map((preset) => (
<SelectItem key={preset.id} value={preset.id} className="text-xs">
{preset.name}
</SelectItem>
))}
</SelectContent>
</Select>
</FormItem>
</div>
</motion.div>
</AnimatePresence>
@@ -1,4 +1,5 @@
import { Loader2, Mic } from 'lucide-react';
import { useEffect } from 'react';
import { Button } from '@/components/ui/button';
import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card';
import {
@@ -19,10 +20,23 @@ import {
SelectValue,
} from '@/components/ui/select';
import { Textarea } from '@/components/ui/textarea';
import { LANGUAGE_OPTIONS } from '@/lib/constants/languages';
import { getLanguageOptionsForEngine, type LanguageCode } from '@/lib/constants/languages';
import { useGenerationForm } from '@/lib/hooks/useGenerationForm';
import { useProfile } from '@/lib/hooks/useProfiles';
import { useUIStore } from '@/stores/uiStore';
import {
applyEngineSelection,
EngineModelSelector,
getEngineDescription,
} from './EngineModelSelector';
import { ParalinguisticInput } from './ParalinguisticInput';
function getEngineSelectValue(engine: string): string {
if (engine === 'qwen') return 'qwen:1.7B';
if (engine === 'qwen_custom_voice') return 'qwen_custom_voice:1.7B';
if (engine === 'tada') return 'tada:1B';
return engine;
}
export function GenerationForm() {
const selectedProfileId = useUIStore((state) => state.selectedProfileId);
@@ -30,6 +44,21 @@ export function GenerationForm() {
const { form, handleSubmit, isPending } = useGenerationForm();
useEffect(() => {
if (!selectedProfile) {
return;
}
if (selectedProfile.language) {
form.setValue('language', selectedProfile.language as LanguageCode);
}
const preferredEngine = selectedProfile.default_engine || selectedProfile.preset_engine;
if (preferredEngine) {
applyEngineSelection(form, getEngineSelectValue(preferredEngine));
}
}, [form, selectedProfile]);
async function onSubmit(data: Parameters<typeof handleSubmit>[0]) {
await handleSubmit(data, selectedProfileId);
}
@@ -64,87 +93,90 @@ export function GenerationForm() {
<FormItem>
<FormLabel>Text to Speak</FormLabel>
<FormControl>
<Textarea
placeholder="Enter the text you want to generate..."
className="min-h-[150px]"
{...field}
/>
</FormControl>
<FormDescription>Max 5000 characters</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name="instruct"
render={({ field }) => (
<FormItem>
<FormLabel>Delivery Instructions (optional)</FormLabel>
<FormControl>
<Textarea
placeholder="e.g. Speak slowly with emphasis, Warm and friendly tone, Professional and authoritative..."
className="min-h-[80px]"
{...field}
/>
{form.watch('engine') === 'chatterbox_turbo' ? (
<ParalinguisticInput
value={field.value}
onChange={field.onChange}
placeholder="Enter text... type / for effects like [laugh], [sigh]"
className="min-h-[150px] rounded-md border border-input bg-background px-3 py-2"
/>
) : (
<Textarea
placeholder="Enter the text you want to generate..."
className="min-h-[150px]"
{...field}
/>
)}
</FormControl>
<FormDescription>
Natural language instructions to control speech delivery (tone, emotion, pace).
Max 500 characters
{form.watch('engine') === 'chatterbox_turbo'
? 'Max 5000 characters. Type / to insert sound effects.'
: 'Max 5000 characters'}
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
<div className="grid gap-4 md:grid-cols-3">
{form.watch('engine') === 'qwen_custom_voice' && (
<FormField
control={form.control}
name="language"
name="instruct"
render={({ field }) => (
<FormItem>
<FormLabel>Language</FormLabel>
<Select onValueChange={field.onChange} defaultValue={field.value}>
<FormControl>
<SelectTrigger>
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
{LANGUAGE_OPTIONS.map((lang) => (
<SelectItem key={lang.value} value={lang.value}>
{lang.label}
</SelectItem>
))}
</SelectContent>
</Select>
<FormLabel>Delivery Instructions (optional)</FormLabel>
<FormControl>
<Textarea
placeholder="e.g. Speak slowly with emphasis, Warm and friendly tone, Professional and authoritative..."
className="min-h-[80px]"
{...field}
/>
</FormControl>
<FormDescription>
Natural language instructions to control speech delivery (tone, emotion,
pace). Max 500 characters
</FormDescription>
<FormMessage />
</FormItem>
)}
/>
)}
<div className="grid gap-4 md:grid-cols-3">
<FormItem>
<FormLabel>Model</FormLabel>
<EngineModelSelector form={form} selectedProfile={selectedProfile} />
<FormDescription>
{getEngineDescription(form.watch('engine') || 'qwen')}
</FormDescription>
</FormItem>
<FormField
control={form.control}
name="modelSize"
render={({ field }) => (
<FormItem>
<FormLabel>Model Size</FormLabel>
<Select onValueChange={field.onChange} defaultValue={field.value}>
<FormControl>
<SelectTrigger>
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
<SelectItem value="1.7B">Qwen TTS 1.7B (Higher Quality)</SelectItem>
<SelectItem value="0.6B">Qwen TTS 0.6B (Faster)</SelectItem>
</SelectContent>
</Select>
<FormDescription>Larger models produce better quality</FormDescription>
<FormMessage />
</FormItem>
)}
name="language"
render={({ field }) => {
const engineLangs = getLanguageOptionsForEngine(form.watch('engine') || 'qwen');
return (
<FormItem>
<FormLabel>Language</FormLabel>
<Select onValueChange={field.onChange} value={field.value}>
<FormControl>
<SelectTrigger>
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
{engineLangs.map((lang) => (
<SelectItem key={lang.value} value={lang.value}>
{lang.label}
</SelectItem>
))}
</SelectContent>
</Select>
<FormMessage />
</FormItem>
);
}}
/>
<FormField
@@ -170,11 +202,7 @@ export function GenerationForm() {
/>
</div>
<Button
type="submit"
className="w-full"
disabled={isPending || !selectedProfileId}
>
<Button type="submit" className="w-full" disabled={isPending || !selectedProfileId}>
{isPending ? (
<>
<Loader2 className="mr-2 h-4 w-4 animate-spin" />
@@ -0,0 +1,422 @@
/**
* ParalinguisticInput — a contentEditable rich text input that renders
* Chatterbox Turbo paralinguistic tags (e.g. [laugh]) as inline badges.
*
* Trigger: typing "/" opens an autocomplete dropdown.
* Paste: pasting text with [tag] patterns auto-converts to badges.
* Output: serializes badges back to plain [tag] text for the API.
*/
import { AnimatePresence, motion } from 'framer-motion';
import { forwardRef, useCallback, useEffect, useImperativeHandle, useRef, useState } from 'react';
import { createPortal } from 'react-dom';
import { cn } from '@/lib/utils/cn';
// ── Tag definitions ─────────────────────────────────────────────────
const PARALINGUISTIC_TAGS = [
{ tag: '[laugh]', label: 'laugh', emoji: '\u{1F602}' },
{ tag: '[chuckle]', label: 'chuckle', emoji: '\u{1F60F}' },
{ tag: '[gasp]', label: 'gasp', emoji: '\u{1F62E}' },
{ tag: '[cough]', label: 'cough', emoji: '\u{1F637}' },
{ tag: '[sigh]', label: 'sigh', emoji: '\u{1F614}' },
{ tag: '[groan]', label: 'groan', emoji: '\u{1F629}' },
{ tag: '[sniff]', label: 'sniff', emoji: '\u{1F443}' },
{ tag: '[shush]', label: 'shush', emoji: '\u{1F92B}' },
{ tag: '[clear throat]', label: 'clear throat', emoji: '\u{1F64A}' },
] as const;
const TAG_REGEX = /\[(laugh|chuckle|gasp|cough|sigh|groan|sniff|shush|clear throat)\]/gi;
// Data attribute used to identify badge spans in the DOM
const BADGE_ATTR = 'data-ptag';
// ── Helpers ─────────────────────────────────────────────────────────
/** Build an inline badge <span> for a tag. */
function makeBadgeHTML(tag: string): string {
const entry = PARALINGUISTIC_TAGS.find((t) => t.tag.toLowerCase() === tag.toLowerCase());
const label = entry?.label ?? tag.replace(/[[\]]/g, '');
const emoji = entry?.emoji ?? '';
// Non-editable inline badge. Zero-width spaces around it let the
// caret sit on either side so the user can type before/after.
return `\u200B<span ${BADGE_ATTR}="${tag}" contenteditable="false" class="ptag-badge">${emoji ? `${emoji}\u00A0` : ''}${label}</span>\u200B`;
}
/** Convert plain text with [tag] patterns into HTML with badge spans. */
function textToHTML(text: string): string {
// Escape HTML entities first
const escaped = text.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
// Replace tag patterns with badge HTML
return escaped.replace(TAG_REGEX, (match) => makeBadgeHTML(match));
}
/** Serialize the contentEditable innerHTML back to plain text with [tag] syntax. */
function htmlToText(container: HTMLElement): string {
let result = '';
for (const node of container.childNodes) {
if (node.nodeType === Node.TEXT_NODE) {
// Strip zero-width spaces we added around badges
result += (node.textContent ?? '').replace(/\u200B/g, '');
} else if (node.nodeType === Node.ELEMENT_NODE) {
const el = node as HTMLElement;
if (el.hasAttribute(BADGE_ATTR)) {
result += el.getAttribute(BADGE_ATTR) ?? '';
} else if (el.tagName === 'BR') {
result += '\n';
} else {
// Recurse for nested elements (e.g. spans from paste)
result += htmlToText(el);
}
}
}
return result;
}
/** Get the text content from the current caret position back to the last
* whitespace or start of container, to detect the "/" trigger. */
function getWordBeforeCaret(_container: HTMLElement): { word: string; range: Range | null } {
const sel = window.getSelection();
if (!sel || sel.rangeCount === 0) return { word: '', range: null };
const range = sel.getRangeAt(0).cloneRange();
range.collapse(true);
// Walk backwards from caret through the text node
const textNode = range.startContainer;
if (textNode.nodeType !== Node.TEXT_NODE) return { word: '', range: null };
const text = textNode.textContent ?? '';
const offset = range.startOffset;
let start = offset;
while (
start > 0 &&
text[start - 1] !== ' ' &&
text[start - 1] !== '\n' &&
text[start - 1] !== '\u00A0'
) {
start--;
}
const word = text.slice(start, offset);
const wordRange = document.createRange();
wordRange.setStart(textNode, start);
wordRange.setEnd(textNode, offset);
return { word, range: wordRange };
}
// ── Component ───────────────────────────────────────────────────────
export interface ParalinguisticInputProps {
value?: string;
onChange?: (value: string) => void;
placeholder?: string;
disabled?: boolean;
className?: string;
style?: React.CSSProperties;
onClick?: () => void;
onFocus?: () => void;
}
export interface ParalinguisticInputRef {
focus: () => void;
element: HTMLDivElement | null;
}
export const ParalinguisticInput = forwardRef<ParalinguisticInputRef, ParalinguisticInputProps>(
function ParalinguisticInput(
{ value, onChange, placeholder, disabled, className, style, onClick, onFocus },
ref,
) {
const editorRef = useRef<HTMLDivElement>(null);
const [showMenu, setShowMenu] = useState(false);
const [menuFilter, setMenuFilter] = useState('');
const [menuIndex, setMenuIndex] = useState(0);
const [menuPosition, setMenuPosition] = useState<{ bottom: number; left: number }>({
bottom: 0,
left: 0,
});
const triggerRangeRef = useRef<Range | null>(null);
const lastSerializedRef = useRef<string>('');
const isComposingRef = useRef(false);
useImperativeHandle(ref, () => ({
focus: () => editorRef.current?.focus(),
element: editorRef.current,
}));
// Filtered tag list for the autocomplete menu
const filteredTags = PARALINGUISTIC_TAGS.filter((t) =>
t.label.toLowerCase().includes(menuFilter.toLowerCase()),
);
// ── Sync external value → editor ──────────────────────────────
useEffect(() => {
const el = editorRef.current;
if (!el) return;
// Only update DOM if the external value differs from what we last emitted
if (value !== undefined && value !== lastSerializedRef.current) {
lastSerializedRef.current = value;
el.innerHTML = value ? textToHTML(value) : '';
}
}, [value]);
// ── Emit plain-text value on input ────────────────────────────
const emitChange = useCallback(() => {
const el = editorRef.current;
if (!el || !onChange) return;
const text = htmlToText(el);
lastSerializedRef.current = text;
onChange(text);
}, [onChange]);
// ── Insert a tag badge at the caret ───────────────────────────
const insertTag = useCallback(
(tag: string) => {
const el = editorRef.current;
if (!el) return;
// Delete the /filter text
const wordRange = triggerRangeRef.current;
if (wordRange) {
wordRange.deleteContents();
}
// Insert badge HTML
const temp = document.createElement('span');
temp.innerHTML = makeBadgeHTML(tag);
const frag = document.createDocumentFragment();
let lastNode: Node | null = null;
while (temp.firstChild) {
lastNode = frag.appendChild(temp.firstChild);
}
const sel = window.getSelection();
if (sel && sel.rangeCount > 0) {
const range = sel.getRangeAt(0);
range.deleteContents();
range.insertNode(frag);
// Move caret after the badge
if (lastNode) {
const newRange = document.createRange();
newRange.setStartAfter(lastNode);
newRange.collapse(true);
sel.removeAllRanges();
sel.addRange(newRange);
}
}
setShowMenu(false);
setMenuFilter('');
emitChange();
el.focus();
},
[emitChange],
);
// ── Handle keydown for autocomplete navigation ────────────────
const handleKeyDown = useCallback(
(e: React.KeyboardEvent) => {
if (showMenu) {
if (filteredTags.length === 0) {
if (e.key === 'Escape') {
e.preventDefault();
setShowMenu(false);
}
return;
}
if (e.key === 'ArrowDown') {
e.preventDefault();
setMenuIndex((i) => (i + 1) % filteredTags.length);
} else if (e.key === 'ArrowUp') {
e.preventDefault();
setMenuIndex((i) => (i - 1 + filteredTags.length) % filteredTags.length);
} else if (e.key === 'Enter' || e.key === 'Tab') {
e.preventDefault();
if (filteredTags[menuIndex]) {
insertTag(filteredTags[menuIndex].tag);
}
} else if (e.key === 'Escape') {
e.preventDefault();
setShowMenu(false);
}
} else {
// Prevent Enter from creating <div> blocks in contentEditable
if (e.key === 'Enter' && !e.shiftKey) {
// Let the form handle submit
}
}
},
[showMenu, filteredTags, menuIndex, insertTag],
);
// ── Handle input (check for / trigger) ────────────────────────
const handleInput = useCallback(() => {
if (isComposingRef.current) return;
const el = editorRef.current;
if (!el) return;
const { word, range } = getWordBeforeCaret(el);
if (word.startsWith('/')) {
const filter = word.slice(1); // strip the /
setMenuFilter(filter);
setMenuIndex(0);
triggerRangeRef.current = range;
// Position the menu above the caret using viewport coords (portalled)
const sel = window.getSelection();
if (sel && sel.rangeCount > 0) {
const rect = sel.getRangeAt(0).getBoundingClientRect();
setMenuPosition({
bottom: window.innerHeight - rect.top + 4,
left: rect.left,
});
}
setShowMenu(true);
} else {
setShowMenu(false);
}
emitChange();
}, [emitChange]);
// ── Handle paste — convert [tag] patterns to badges ───────────
const handlePaste = useCallback(
(e: React.ClipboardEvent) => {
e.preventDefault();
const text = e.clipboardData.getData('text/plain');
if (!text) return;
const el = editorRef.current;
if (!el) return;
const html = textToHTML(text);
// Insert at caret
const sel = window.getSelection();
if (sel && sel.rangeCount > 0) {
const range = sel.getRangeAt(0);
range.deleteContents();
const temp = document.createElement('div');
temp.innerHTML = html;
const frag = document.createDocumentFragment();
let lastNode: Node | null = null;
while (temp.firstChild) {
lastNode = frag.appendChild(temp.firstChild);
}
range.insertNode(frag);
if (lastNode) {
const newRange = document.createRange();
newRange.setStartAfter(lastNode);
newRange.collapse(true);
sel.removeAllRanges();
sel.addRange(newRange);
}
}
emitChange();
},
[emitChange],
);
// ── Show placeholder ──────────────────────────────────────────
const isEmpty = !value || value.trim() === '';
return (
<div className="relative">
{/* Placeholder */}
{isEmpty && placeholder && (
<div
className="pointer-events-none absolute inset-0 text-sm text-muted-foreground/60 px-3 py-2 select-none"
aria-hidden
>
{placeholder}
</div>
)}
{/* Editable area */}
<div
ref={editorRef}
contentEditable={!disabled}
suppressContentEditableWarning
role={disabled ? undefined : 'textbox'}
aria-multiline={disabled ? undefined : true}
aria-placeholder={placeholder}
aria-disabled={disabled}
tabIndex={disabled ? -1 : 0}
className={cn(
'min-h-[32px] text-sm whitespace-pre-wrap break-words outline-none',
'[&_.ptag-badge]:inline-flex [&_.ptag-badge]:items-center [&_.ptag-badge]:rounded-full',
'[&_.ptag-badge]:bg-accent/20 [&_.ptag-badge]:text-accent [&_.ptag-badge]:border [&_.ptag-badge]:border-accent/30',
'[&_.ptag-badge]:px-2 [&_.ptag-badge]:py-0 [&_.ptag-badge]:text-xs [&_.ptag-badge]:font-medium',
'[&_.ptag-badge]:mx-0.5 [&_.ptag-badge]:select-none [&_.ptag-badge]:cursor-default',
'[&_.ptag-badge]:align-baseline',
disabled && 'opacity-50 cursor-not-allowed',
className,
)}
style={style}
onInput={!disabled ? handleInput : undefined}
onKeyDown={!disabled ? handleKeyDown : undefined}
onPaste={!disabled ? handlePaste : undefined}
onClick={!disabled ? onClick : undefined}
onFocus={!disabled ? onFocus : undefined}
onBlur={() => {
setShowMenu(false);
triggerRangeRef.current = null;
}}
onCompositionStart={() => {
isComposingRef.current = true;
}}
onCompositionEnd={() => {
isComposingRef.current = false;
handleInput();
}}
/>
{/* Autocomplete dropdown — portalled to body, positioned above the caret */}
{showMenu &&
filteredTags.length > 0 &&
createPortal(
<AnimatePresence>
<motion.div
initial={{ opacity: 0, y: 4 }}
animate={{ opacity: 1, y: 0 }}
exit={{ opacity: 0, y: 4 }}
transition={{ duration: 0.12 }}
className="fixed z-[9999] min-w-[200px] max-h-[280px] overflow-y-auto rounded-lg border border-border bg-popover shadow-lg"
style={{
bottom: menuPosition.bottom,
left: menuPosition.left,
}}
>
{filteredTags.map((t, i) => (
<button
key={t.tag}
type="button"
className={cn(
'flex items-center gap-2 w-full px-3 py-1.5 text-sm text-left transition-colors',
i === menuIndex
? 'bg-accent/20 text-accent-foreground'
: 'text-popover-foreground hover:bg-muted/50',
)}
onMouseDown={(e) => {
e.preventDefault(); // Keep focus in editor
insertTag(t.tag);
}}
onMouseEnter={() => setMenuIndex(i)}
>
<span className="text-base leading-none">{t.emoji}</span>
<span>{t.label}</span>
<span className="ml-auto text-xs text-muted-foreground font-mono">{t.tag}</span>
</button>
))}
</motion.div>
</AnimatePresence>,
document.body,
)}
</div>
);
},
);
+641 -87
View File
@@ -1,13 +1,21 @@
import { useMutation, useQueryClient } from '@tanstack/react-query';
import { AnimatePresence, motion } from 'framer-motion';
import {
AudioWaveform,
AudioLines,
Download,
FileArchive,
Loader2,
MoreHorizontal,
Play,
RotateCcw,
Square,
Star,
Trash2,
Wand2,
} from 'lucide-react';
import { useEffect, useRef, useState } from 'react';
import { EffectsChainEditor } from '@/components/Effects/EffectsChainEditor';
import { Button } from '@/components/ui/button';
import {
Dialog,
@@ -23,12 +31,20 @@ import {
DropdownMenuItem,
DropdownMenuTrigger,
} from '@/components/ui/dropdown-menu';
import {
Select,
SelectContent,
SelectItem,
SelectTrigger,
SelectValue,
} from '@/components/ui/select';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import type { HistoryResponse } from '@/lib/api/types';
import type { EffectConfig, GenerationVersionResponse, HistoryResponse } from '@/lib/api/types';
import { BOTTOM_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import {
useClearFailedGenerations,
useDeleteGeneration,
useExportGeneration,
useExportGenerationAudio,
@@ -36,11 +52,39 @@ import {
useImportGeneration,
} from '@/lib/hooks/useHistory';
import { cn } from '@/lib/utils/cn';
import { formatDate, formatDuration } from '@/lib/utils/format';
import { formatDate, formatDuration, formatEngineName } from '@/lib/utils/format';
import { useGenerationStore } from '@/stores/generationStore';
import { usePlayerStore } from '@/stores/playerStore';
// OLD TABLE-BASED COMPONENT - REMOVED (can be found in git history)
// This is the new alternate history view with fixed height rows
// ─── Audio Bars ─────────────────────────────────────────────────────────────
function AudioBars({ mode }: { mode: 'idle' | 'generating' | 'playing' }) {
const barColor = mode !== 'idle' ? 'bg-accent' : 'bg-muted-foreground/40';
return (
<div className="flex items-center gap-[2px] h-5">
{[0, 1, 2, 3, 4].map((i) => (
<motion.div
key={`${mode}-${i}`}
className={`w-[3px] rounded-full ${barColor}`}
animate={
mode === 'generating'
? { height: ['6px', '16px', '6px'] }
: mode === 'playing'
? { height: ['8px', '14px', '4px', '12px', '8px'] }
: { height: '8px' }
}
transition={
mode === 'generating'
? { duration: 0.6, repeat: Infinity, delay: i * 0.08, ease: 'easeInOut' }
: mode === 'playing'
? { duration: 1.2, repeat: Infinity, delay: i * 0.15, ease: 'easeInOut' }
: { duration: 0.4, ease: 'easeOut' }
}
/>
))}
</div>
);
}
// NEW ALTERNATE HISTORY VIEW - FIXED HEIGHT ROWS WITH INFINITE SCROLL
export function HistoryTable() {
@@ -53,8 +97,22 @@ export function HistoryTable() {
const fileInputRef = useRef<HTMLInputElement>(null);
const [importDialogOpen, setImportDialogOpen] = useState(false);
const [selectedFile, setSelectedFile] = useState<File | null>(null);
const [deleteDialogOpen, setDeleteDialogOpen] = useState(false);
const [generationToDelete, setGenerationToDelete] = useState<{ id: string; name: string } | null>(
null,
);
const [effectsDialogOpen, setEffectsDialogOpen] = useState(false);
const [effectsTargetId, setEffectsTargetId] = useState<string | null>(null);
const [effectsTargetVersions, setEffectsTargetVersions] = useState<GenerationVersionResponse[]>(
[],
);
const [effectsSourceVersionId, setEffectsSourceVersionId] = useState<string | null>(null);
const [effectsChain, setEffectsChain] = useState<EffectConfig[]>([]);
const [applyingEffects, setApplyingEffects] = useState(false);
const [expandedVersionsId, setExpandedVersionsId] = useState<string | null>(null);
const limit = 20;
const { toast } = useToast();
const queryClient = useQueryClient();
const {
data: historyData,
@@ -66,9 +124,29 @@ export function HistoryTable() {
});
const deleteGeneration = useDeleteGeneration();
const clearFailed = useClearFailedGenerations();
const [clearFailedDialogOpen, setClearFailedDialogOpen] = useState(false);
const exportGeneration = useExportGeneration();
const exportGenerationAudio = useExportGenerationAudio();
const importGeneration = useImportGeneration();
const cancelGeneration = useMutation({
mutationFn: (generationId: string) => apiClient.cancelGeneration(generationId),
onSuccess: async (data) => {
await queryClient.invalidateQueries({ queryKey: ['history'] });
toast({
title: 'Cancelling generation',
description: data.message,
});
},
onError: (error) => {
toast({
title: 'Cancel failed',
description: error instanceof Error ? error.message : 'Could not cancel generation',
variant: 'destructive',
});
},
});
const addPendingGeneration = useGenerationStore((state) => state.addPendingGeneration);
const setAudioWithAutoPlay = usePlayerStore((state) => state.setAudioWithAutoPlay);
const restartCurrentAudio = usePlayerStore((state) => state.restartCurrentAudio);
const currentAudioId = usePlayerStore((state) => state.audioId);
@@ -94,13 +172,28 @@ export function HistoryTable() {
}
}, [historyData, page]);
// Reset to page 0 when deletions or imports occur
// Reset to page 0 when deletions, imports, or generation completions occur
const pendingCount = useGenerationStore((state) => state.pendingGenerationIds.size);
const prevPendingCountRef = useRef(pendingCount);
useEffect(() => {
if (deleteGeneration.isSuccess || importGeneration.isSuccess) {
if (deleteGeneration.isSuccess || importGeneration.isSuccess || clearFailed.isSuccess) {
setPage(0);
setAllHistory([]);
}
}, [deleteGeneration.isSuccess, importGeneration.isSuccess]);
}, [deleteGeneration.isSuccess, importGeneration.isSuccess, clearFailed.isSuccess]);
useEffect(() => {
// A generation finished (pending count decreased) — scroll back to show it
if (
prevPendingCountRef.current > 0 &&
pendingCount < prevPendingCountRef.current &&
page !== 0
) {
setPage(0);
setAllHistory([]);
}
prevPendingCountRef.current = pendingCount;
}, [pendingCount, page]);
// Intersection Observer for infinite scroll
useEffect(() => {
@@ -179,6 +272,133 @@ export function HistoryTable() {
);
};
const handleDeleteClick = (generationId: string, profileName: string) => {
setGenerationToDelete({ id: generationId, name: profileName });
setDeleteDialogOpen(true);
};
const handleDeleteConfirm = () => {
if (generationToDelete) {
deleteGeneration.mutate(generationToDelete.id);
setDeleteDialogOpen(false);
setGenerationToDelete(null);
}
};
const handleRetry = async (generationId: string) => {
try {
const result = await apiClient.retryGeneration(generationId);
addPendingGeneration(result.id);
queryClient.invalidateQueries({ queryKey: ['history'] });
} catch (error) {
toast({
title: 'Retry failed',
description: error instanceof Error ? error.message : 'Could not retry generation',
variant: 'destructive',
});
}
};
const handleRegenerate = async (generationId: string) => {
try {
await apiClient.regenerateGeneration(generationId);
addPendingGeneration(generationId);
queryClient.invalidateQueries({ queryKey: ['history'] });
} catch (error) {
toast({
title: 'Regenerate failed',
description: error instanceof Error ? error.message : 'Could not regenerate',
variant: 'destructive',
});
}
};
const handleToggleFavorite = async (generationId: string) => {
try {
await apiClient.toggleFavorite(generationId);
queryClient.invalidateQueries({ queryKey: ['history'] });
} catch (error) {
toast({
title: 'Failed to update favorite',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
}
};
const handleApplyEffects = (generationId: string) => {
const gen = allHistory.find((g) => g.id === generationId);
const versions = gen?.versions ?? [];
setEffectsTargetId(generationId);
setEffectsTargetVersions(versions);
// Default to clean/original version (no effects chain)
const cleanVersion = versions.find((v) => !v.effects_chain || v.effects_chain.length === 0);
setEffectsSourceVersionId(cleanVersion?.id ?? null);
setEffectsChain([]);
setEffectsDialogOpen(true);
};
const handleApplyEffectsConfirm = async () => {
if (!effectsTargetId || effectsChain.length === 0) return;
setApplyingEffects(true);
try {
const newVersion = await apiClient.applyEffectsToGeneration(effectsTargetId, {
effects_chain: effectsChain,
source_version_id: effectsSourceVersionId ?? undefined,
set_as_default: true,
});
queryClient.invalidateQueries({ queryKey: ['history'] });
// If the player is currently on this generation, reload with the new version audio
if (currentAudioId === effectsTargetId) {
const gen = allHistory.find((g) => g.id === effectsTargetId);
if (gen) {
const versionUrl = apiClient.getVersionAudioUrl(newVersion.id);
setAudioWithAutoPlay(
versionUrl,
effectsTargetId,
gen.profile_id,
gen.text.substring(0, 50),
);
}
}
setEffectsDialogOpen(false);
toast({ title: 'Effects applied', description: 'A new version has been created.' });
} catch (error) {
toast({
title: 'Failed to apply effects',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setApplyingEffects(false);
}
};
const handleSwitchVersion = async (generationId: string, versionId: string) => {
try {
await apiClient.setDefaultVersion(generationId, versionId);
queryClient.invalidateQueries({ queryKey: ['history'] });
} catch (error) {
toast({
title: 'Failed to switch version',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
}
};
const handlePlayVersion = (
generationId: string,
versionId: string,
text: string,
profileId: string,
) => {
const audioUrl = apiClient.getVersionAudioUrl(versionId);
setAudioWithAutoPlay(audioUrl, generationId, profileId, text.substring(0, 50));
};
const handleImportConfirm = () => {
if (selectedFile) {
importGeneration.mutate(selectedFile, {
@@ -214,6 +434,27 @@ export function HistoryTable() {
const history = allHistory;
const hasMore = allHistory.length < total;
const failedCount = history.filter((g) => g.status === 'failed').length;
const handleClearFailedConfirm = () => {
clearFailed.mutate(undefined, {
onSuccess: (data) => {
setClearFailedDialogOpen(false);
toast({
title: 'Cleared failed generations',
description: `${data.deleted} failed ${data.deleted === 1 ? 'generation' : 'generations'} removed.`,
});
},
onError: (error) => {
setClearFailedDialogOpen(false);
toast({
title: 'Failed to clear',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
},
});
};
return (
<div className="flex flex-col h-full min-h-0 relative">
@@ -223,6 +464,23 @@ export function HistoryTable() {
</div>
) : (
<>
{failedCount > 0 && (
<div className="flex items-center justify-between px-1 pb-2">
<span className="text-xs text-muted-foreground">
{failedCount} failed {failedCount === 1 ? 'generation' : 'generations'}
</span>
<Button
variant="ghost"
size="sm"
className="h-7 text-xs text-muted-foreground hover:text-destructive"
onClick={() => setClearFailedDialogOpen(true)}
disabled={clearFailed.isPending}
>
<Trash2 className="h-3 w-3 mr-1.5" />
{clearFailed.isPending ? 'Clearing...' : 'Clear failed'}
</Button>
</div>
)}
{isScrolled && (
<div className="absolute top-0 left-0 right-0 h-16 bg-gradient-to-b from-background to-transparent z-10 pointer-events-none" />
)}
@@ -235,101 +493,291 @@ export function HistoryTable() {
>
{history.map((gen) => {
const isCurrentlyPlaying = currentAudioId === gen.id && isPlaying;
const isInProgress = gen.status === 'loading_model' || gen.status === 'generating';
const isGenerating = isInProgress;
const isFailed = gen.status === 'failed';
const isPlayable = !isGenerating && !isFailed;
const hasVersions = gen.versions && gen.versions.length > 1;
const isVersionsExpanded = expandedVersionsId === gen.id;
const isCancelling =
cancelGeneration.isPending && cancelGeneration.variables === gen.id;
return (
<div
key={gen.id}
className={cn(
'flex items-stretch gap-4 h-26 border rounded-md p-3 bg-card hover:bg-muted/70 transition-colors text-left w-full',
'border rounded-md bg-card transition-colors text-left w-full',
isCurrentlyPlaying && 'bg-muted/70',
)}
onMouseDown={(e) => {
// Don't trigger play if clicking on textarea or if text is selected
const target = e.target as HTMLElement;
if (target.closest('textarea') || window.getSelection()?.toString()) {
return;
}
handlePlay(gen.id, gen.text, gen.profile_id);
}}
>
{/* Waveform icon */}
<div className="flex items-center shrink-0">
<AudioWaveform className="h-5 w-5 text-muted-foreground" />
</div>
{/* Left side - Meta information */}
<div className="flex flex-col gap-1.5 w-48 shrink-0 justify-center">
<div className="font-medium text-sm truncate" title={gen.profile_name}>
{gen.profile_name}
</div>
<div className="flex items-center gap-2">
<span className="text-xs text-muted-foreground">{gen.language}</span>
<span className="text-xs text-muted-foreground">
{formatDuration(gen.duration)}
</span>
</div>
<div className="text-xs text-muted-foreground">
{formatDate(gen.created_at)}
</div>
</div>
{/* Right side - Transcript textarea */}
<div className="flex-1 min-w-0 flex">
<Textarea
value={gen.text}
className="flex-1 resize-none text-sm text-muted-foreground select-text"
readOnly
/>
</div>
{/* Far right - Ellipsis actions */}
{/* Main row */}
<div
className="w-10 shrink-0 flex justify-end"
onMouseDown={(e) => e.stopPropagation()}
onClick={(e) => e.stopPropagation()}
role={isPlayable ? 'button' : undefined}
tabIndex={isPlayable ? 0 : undefined}
className={cn(
'flex items-stretch gap-4 h-26 p-3 outline-none',
isPlayable && 'hover:bg-muted/70 cursor-pointer rounded-md',
isVersionsExpanded && 'rounded-b-none',
)}
aria-label={
isGenerating
? `Generating speech for ${gen.profile_name}...`
: isFailed
? `Generation failed for ${gen.profile_name}`
: isCurrentlyPlaying
? `Sample from ${gen.profile_name}, ${formatDuration(gen.duration ?? 0)}, ${formatDate(gen.created_at)}. Playing. Press Enter to restart.`
: `Sample from ${gen.profile_name}, ${formatDuration(gen.duration ?? 0)}, ${formatDate(gen.created_at)}. Press Enter to play.`
}
onMouseDown={(e) => {
if (!isPlayable) return;
const target = e.target as HTMLElement;
if (target.closest('textarea') || window.getSelection()?.toString()) {
return;
}
handlePlay(gen.id, gen.text, gen.profile_id);
}}
onKeyDown={(e) => {
if (!isPlayable) return;
const target = e.target as HTMLElement;
if (target.closest('textarea') || target.closest('button')) return;
if (e.key === 'Enter' || e.key === ' ') {
e.preventDefault();
handlePlay(gen.id, gen.text, gen.profile_id);
}
}}
>
<DropdownMenu>
<DropdownMenuTrigger asChild>
{/* Status icon */}
<div className="flex items-center shrink-0 w-10 justify-center overflow-hidden">
<AudioBars
mode={isGenerating ? 'generating' : isCurrentlyPlaying ? 'playing' : 'idle'}
/>
</div>
{/* Left side - Meta information */}
<div className="flex flex-col gap-1.5 w-48 shrink-0 justify-center">
<div className="font-medium text-sm truncate" title={gen.profile_name}>
{gen.profile_name}
</div>
<div className="flex items-center gap-2">
<span className="text-xs text-muted-foreground">{gen.language}</span>
<span className="text-xs text-muted-foreground">
{formatEngineName(gen.engine, gen.model_size)}
</span>
{isFailed ? (
<span className="text-xs text-destructive">Failed</span>
) : !isGenerating ? (
<span className="text-xs text-muted-foreground">
{formatDuration(gen.duration ?? 0)}
</span>
) : null}
</div>
<div className="text-xs text-muted-foreground">
{isInProgress ? (
<span className="text-accent">
{gen.status === 'loading_model' ? 'Loading model...' : 'Generating...'}
</span>
) : (
formatDate(gen.created_at)
)}
</div>
</div>
{/* Right side - Transcript textarea */}
<div className="flex-1 min-w-0 flex">
<Textarea
value={gen.text}
className="flex-1 resize-none text-sm text-muted-foreground select-text"
readOnly
aria-label={`Transcript for sample from ${gen.profile_name}, ${formatDuration(gen.duration ?? 0)}`}
/>
</div>
{/* Far right - Actions */}
<div
className="shrink-0 flex flex-col justify-center items-center gap-0.5"
onMouseDown={(e) => e.stopPropagation()}
onClick={(e) => e.stopPropagation()}
>
<Button
variant="ghost"
size="icon"
className={cn(
'h-6 w-6 text-muted-foreground/50 hover:bg-muted-foreground/20 hover:text-muted-foreground',
gen.is_favorited && 'text-accent hover:text-accent',
)}
aria-label={gen.is_favorited ? 'Unfavorite' : 'Favorite'}
onClick={() => handleToggleFavorite(gen.id)}
>
<Star
className="h-2 w-2"
fill={gen.is_favorited ? 'currentColor' : 'none'}
/>
</Button>
{hasVersions && (
<Button
variant="ghost"
size="icon"
className="h-8 w-8"
aria-label="Actions"
className={cn(
'h-6 w-6 text-muted-foreground/50 hover:bg-muted-foreground/20 hover:text-muted-foreground',
isVersionsExpanded && 'text-accent hover:text-accent',
)}
aria-label="Toggle versions"
onClick={() => setExpandedVersionsId(isVersionsExpanded ? null : gen.id)}
>
<MoreHorizontal className="h-4 w-4" />
<AudioLines className="h-2 w-2" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="end">
<DropdownMenuItem
onClick={() => handlePlay(gen.id, gen.text, gen.profile_id)}
)}
{isFailed ? (
<>
<Button
variant="ghost"
size="icon"
className="h-6 w-6 text-muted-foreground/50 hover:bg-muted-foreground/20 hover:text-muted-foreground"
aria-label="Retry generation"
onClick={() => handleRetry(gen.id)}
>
<RotateCcw className="h-2 w-2" />
</Button>
<Button
variant="ghost"
size="icon"
className="h-6 w-6 text-muted-foreground/50 hover:bg-muted-foreground/20 hover:text-muted-foreground"
aria-label="Delete generation"
disabled={deleteGeneration.isPending}
onClick={() => handleDeleteClick(gen.id, gen.profile_name)}
>
<Trash2 className="h-2 w-2" />
</Button>
</>
) : isGenerating ? (
<Button
variant="ghost"
size="icon"
className="h-6 w-6 text-muted-foreground/50 hover:bg-muted-foreground/20 hover:text-muted-foreground"
aria-label="Cancel generation"
disabled={isCancelling}
onClick={() => cancelGeneration.mutate(gen.id)}
>
<Play className="mr-2 h-4 w-4" />
Play
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleDownloadAudio(gen.id, gen.text)}
disabled={exportGenerationAudio.isPending}
>
<Download className="mr-2 h-4 w-4" />
Export Audio
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleExportPackage(gen.id, gen.text)}
disabled={exportGeneration.isPending}
>
<FileArchive className="mr-2 h-4 w-4" />
Export Package
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => deleteGeneration.mutate(gen.id)}
disabled={deleteGeneration.isPending}
className="text-destructive focus:text-destructive"
>
<Trash2 className="mr-2 h-4 w-4" />
Delete
</DropdownMenuItem>
</DropdownMenuContent>
</DropdownMenu>
{isCancelling ? (
<Loader2 className="h-2 w-2 animate-spin" />
) : (
<Square className="h-2 w-2" />
)}
</Button>
) : (
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button
variant="ghost"
size="icon"
className="h-6 w-6 text-muted-foreground/50 hover:bg-muted-foreground/20 hover:text-muted-foreground"
aria-label="Actions"
disabled={isGenerating}
>
<MoreHorizontal className="h-2 w-2" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="end">
<DropdownMenuItem onClick={() => handlePlay(gen.id, gen.text, gen.profile_id)}>
<Play className="mr-2 h-4 w-4" />
Play
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleDownloadAudio(gen.id, gen.text)}
disabled={exportGenerationAudio.isPending}
>
<Download className="mr-2 h-4 w-4" />
Export Audio
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleExportPackage(gen.id, gen.text)}
disabled={exportGeneration.isPending}
>
<FileArchive className="mr-2 h-4 w-4" />
Export Package
</DropdownMenuItem>
<DropdownMenuItem onClick={() => handleApplyEffects(gen.id)}>
<Wand2 className="mr-2 h-4 w-4" />
Apply Effects
</DropdownMenuItem>
<DropdownMenuItem onClick={() => handleRegenerate(gen.id)}>
<RotateCcw className="mr-2 h-4 w-4" />
Regenerate
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleDeleteClick(gen.id, gen.profile_name)}
disabled={deleteGeneration.isPending}
// className="text-destructive focus:text-destructive"
>
<Trash2 className="mr-2 h-4 w-4" />
Delete
</DropdownMenuItem>
</DropdownMenuContent>
</DropdownMenu>
)}
</div>
</div>
{/* Expandable versions panel */}
<AnimatePresence>
{isVersionsExpanded && gen.versions && (
<motion.div
initial={{ height: 0, opacity: 0 }}
animate={{ height: 'auto', opacity: 1 }}
exit={{ height: 0, opacity: 0 }}
transition={{ duration: 0.2, ease: 'easeOut' }}
className="overflow-hidden"
>
<div className="border-t border-border/50">
<div className="divide-y divide-border/40">
{gen.versions.map((v) => {
// Show source provenance when effects were applied to a non-clean version
const sourceVersion = v.source_version_id
? gen.versions?.find((sv) => sv.id === v.source_version_id)
: null;
const showSource =
sourceVersion &&
sourceVersion.effects_chain &&
sourceVersion.effects_chain.length > 0;
return (
<button
key={v.id}
type="button"
className="flex items-center gap-2 w-full h-9 px-3 text-left hover:bg-muted/50 transition-colors"
onClick={() => {
handlePlayVersion(gen.id, v.id, gen.text, gen.profile_id);
if (!v.is_default) {
handleSwitchVersion(gen.id, v.id);
}
}}
>
<AudioLines className="h-3 w-3 shrink-0 text-muted-foreground" />
<span className="truncate text-xs font-medium">{v.label}</span>
{v.effects_chain && v.effects_chain.length > 0 && (
<span className="text-[10px] text-muted-foreground truncate">
{v.effects_chain.map((e) => e.type).join(' → ')}
</span>
)}
{showSource && (
<span className="text-[10px] text-muted-foreground/60 truncate">
from {sourceVersion.label}
</span>
)}
<span className="flex-1" />
{v.is_default && (
<span className="text-[10px] bg-accent/15 text-accent px-1.5 py-0.5 rounded-full">
active
</span>
)}
</button>
);
})}
</div>
</div>
</motion.div>
)}
</AnimatePresence>
</div>
);
})}
@@ -351,6 +799,61 @@ export function HistoryTable() {
</>
)}
<Dialog open={deleteDialogOpen} onOpenChange={setDeleteDialogOpen}>
<DialogContent>
<DialogHeader>
<DialogTitle>Delete Generation</DialogTitle>
<DialogDescription>
Are you sure you want to delete this generation from "{generationToDelete?.name}"?
This action cannot be undone.
</DialogDescription>
</DialogHeader>
<DialogFooter>
<Button
variant="outline"
onClick={() => {
setDeleteDialogOpen(false);
setGenerationToDelete(null);
}}
>
Cancel
</Button>
<Button
variant="destructive"
onClick={handleDeleteConfirm}
disabled={deleteGeneration.isPending}
>
{deleteGeneration.isPending ? 'Deleting...' : 'Delete'}
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
<Dialog open={clearFailedDialogOpen} onOpenChange={setClearFailedDialogOpen}>
<DialogContent>
<DialogHeader>
<DialogTitle>Clear failed generations</DialogTitle>
<DialogDescription>
This will permanently delete {failedCount} failed{' '}
{failedCount === 1 ? 'generation' : 'generations'} from your history. This cannot be
undone.
</DialogDescription>
</DialogHeader>
<DialogFooter>
<Button variant="outline" onClick={() => setClearFailedDialogOpen(false)}>
Cancel
</Button>
<Button
variant="destructive"
onClick={handleClearFailedConfirm}
disabled={clearFailed.isPending}
>
{clearFailed.isPending ? 'Clearing...' : 'Clear all'}
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
<Dialog open={importDialogOpen} onOpenChange={setImportDialogOpen}>
<DialogContent>
<DialogHeader>
@@ -381,6 +884,57 @@ export function HistoryTable() {
</DialogFooter>
</DialogContent>
</Dialog>
<Dialog open={effectsDialogOpen} onOpenChange={setEffectsDialogOpen}>
<DialogContent className="max-w-md">
<DialogHeader>
<DialogTitle>Apply Effects</DialogTitle>
<DialogDescription>
Configure post-processing effects to apply to this generation. A new version will be
created.
</DialogDescription>
</DialogHeader>
{effectsTargetVersions.length > 1 && (
<div className="space-y-1.5">
<label className="text-xs font-medium text-muted-foreground">Source</label>
<Select
value={effectsSourceVersionId ?? ''}
onValueChange={(val) => setEffectsSourceVersionId(val || null)}
>
<SelectTrigger className="h-8 text-xs">
<SelectValue placeholder="Select source version" />
</SelectTrigger>
<SelectContent>
{effectsTargetVersions.map((v) => (
<SelectItem key={v.id} value={v.id} className="text-xs">
{v.label}
{v.effects_chain && v.effects_chain.length > 0 && (
<span className="text-muted-foreground ml-1.5">
({v.effects_chain.map((e) => e.type).join(' + ')})
</span>
)}
</SelectItem>
))}
</SelectContent>
</Select>
</div>
)}
<div className="py-2 max-h-80 overflow-y-auto">
<EffectsChainEditor value={effectsChain} onChange={setEffectsChain} />
</div>
<DialogFooter>
<Button variant="outline" onClick={() => setEffectsDialogOpen(false)}>
Cancel
</Button>
<Button
onClick={handleApplyEffectsConfirm}
disabled={applyingEffects || effectsChain.length === 0}
>
{applyingEffects ? 'Applying...' : 'Apply'}
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
</div>
);
}
+7 -7
View File
@@ -13,7 +13,7 @@ import {
} from '@/components/ui/dialog';
import { useToast } from '@/components/ui/use-toast';
import { ProfileList } from '@/components/VoiceProfiles/ProfileList';
import { BOTTOM_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import { useImportProfile } from '@/lib/hooks/useProfiles';
import { cn } from '@/lib/utils/cn';
import { usePlayerStore } from '@/stores/playerStore';
@@ -77,9 +77,9 @@ export function MainEditor() {
return (
// Main view: Profiles top left, Generator bottom left, History right
<div className="grid grid-cols-1 lg:grid-cols-2 gap-6 h-full min-h-0 overflow-hidden relative">
<div className="grid grid-cols-1 lg:grid-cols-2 lg:gap-6 h-full min-h-0 overflow-hidden relative">
{/* Left Column */}
<div className="flex flex-col min-h-0 overflow-hidden relative">
<div className="flex flex-col min-h-0 overflow-hidden relative lg:overflow-hidden">
{/* Scroll Mask - Always visible, behind content */}
<div className="absolute top-0 left-0 right-0 h-16 bg-gradient-to-b from-background to-transparent z-0 pointer-events-none" />
@@ -110,10 +110,7 @@ export function MainEditor() {
{/* Scrollable Content */}
<div
ref={scrollRef}
className={cn(
'flex-1 min-h-0 overflow-y-auto pt-14',
isPlayerVisible ? BOTTOM_SAFE_AREA_PADDING : 'pb-4',
)}
className={cn('flex-1 min-h-0 overflow-y-auto pt-14 pb-4', isPlayerVisible && 'lg:pb-32')}
>
<div className="flex flex-col gap-6">
<div className="shrink-0 flex flex-col">
@@ -123,6 +120,9 @@ export function MainEditor() {
</div>
</div>
{/* Divider - single column only */}
{/* <div className="border-t border-border -my-3 lg:hidden" /> */}
{/* Right Column - History */}
<div className="flex flex-col min-h-0 overflow-hidden">
<HistoryTable />
+1 -1
View File
@@ -2,7 +2,7 @@ import { ModelManagement } from '@/components/ServerSettings/ModelManagement';
export function ModelsTab() {
return (
<div className="space-y-4 overflow-y-auto flex flex-col">
<div className="h-full flex flex-col">
<ModelManagement />
</div>
);
@@ -1,9 +1,12 @@
import { zodResolver } from '@hookform/resolvers/zod';
import { Loader2, XCircle } from 'lucide-react';
import { useEffect } from 'react';
import { useForm } from 'react-hook-form';
import * as z from 'zod';
import { Badge } from '@/components/ui/badge';
import { Button } from '@/components/ui/button';
import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card';
import { Checkbox } from '@/components/ui/checkbox';
import {
Form,
FormControl,
@@ -14,10 +17,10 @@ import {
FormMessage,
} from '@/components/ui/form';
import { Input } from '@/components/ui/input';
import { Checkbox } from '@/components/ui/checkbox';
import { useToast } from '@/components/ui/use-toast';
import { useServerStore } from '@/stores/serverStore';
import { useServerHealth } from '@/lib/hooks/useServer';
import { usePlatform } from '@/platform/PlatformContext';
import { useServerStore } from '@/stores/serverStore';
const connectionSchema = z.object({
serverUrl: z.string().url('Please enter a valid URL'),
@@ -31,7 +34,10 @@ export function ConnectionForm() {
const setServerUrl = useServerStore((state) => state.setServerUrl);
const keepServerRunningOnClose = useServerStore((state) => state.keepServerRunningOnClose);
const setKeepServerRunningOnClose = useServerStore((state) => state.setKeepServerRunningOnClose);
const mode = useServerStore((state) => state.mode);
const setMode = useServerStore((state) => state.setMode);
const { toast } = useToast();
const { data: health, isLoading, error: healthError } = useServerHealth();
const form = useForm<ConnectionFormValues>({
resolver: zodResolver(connectionSchema),
@@ -49,7 +55,7 @@ export function ConnectionForm() {
function onSubmit(data: ConnectionFormValues) {
setServerUrl(data.serverUrl);
form.reset(data); // Reset form state after successful submission
form.reset(data);
toast({
title: 'Server URL updated',
description: `Connected to ${data.serverUrl}`,
@@ -57,7 +63,7 @@ export function ConnectionForm() {
}
return (
<Card>
<Card role="region" aria-label="Server Connection" tabIndex={0}>
<CardHeader>
<CardTitle>Server Connection</CardTitle>
</CardHeader>
@@ -83,10 +89,42 @@ export function ConnectionForm() {
</form>
</Form>
{/* Connection status */}
<div className="mt-4">
{isLoading ? (
<div className="flex items-center gap-2">
<Loader2 className="h-4 w-4 animate-spin" />
<span className="text-sm text-muted-foreground">Checking connection...</span>
</div>
) : healthError ? (
<div className="flex items-center gap-2">
<XCircle className="h-4 w-4 text-destructive" />
<span className="text-sm text-destructive">
Connection failed: {healthError.message}
</span>
</div>
) : health ? (
<div className="flex flex-wrap gap-2">
<Badge
variant={health.model_loaded || health.model_downloaded ? 'default' : 'secondary'}
>
{health.model_loaded || health.model_downloaded ? 'Model Ready' : 'No Model'}
</Badge>
<Badge variant={health.gpu_available ? 'default' : 'secondary'}>
GPU: {health.gpu_available ? 'Available' : 'Not Available'}
</Badge>
{health.vram_used_mb != null && health.vram_used_mb > 0 && (
<Badge variant="outline">VRAM: {health.vram_used_mb.toFixed(0)} MB</Badge>
)}
</div>
) : null}
</div>
<div className="mt-6 pt-6 border-t">
<div className="flex items-start space-x-3">
<Checkbox
id="keepServerRunning"
className="mt-[6px]"
checked={keepServerRunningOnClose}
onCheckedChange={(checked: boolean) => {
setKeepServerRunningOnClose(checked);
@@ -115,6 +153,39 @@ export function ConnectionForm() {
</div>
</div>
</div>
{platform.metadata.isTauri && (
<div className="mt-6 pt-6 border-t">
<div className="flex items-start space-x-3">
<Checkbox
id="allowNetworkAccess"
className="mt-[6px]"
checked={mode === 'remote'}
onCheckedChange={(checked: boolean) => {
setMode(checked ? 'remote' : 'local');
toast({
title: 'Setting updated',
description: checked
? 'Network access enabled. Restart the app to apply.'
: 'Network access disabled. Restart the app to apply.',
});
}}
/>
<div className="space-y-1">
<label
htmlFor="allowNetworkAccess"
className="text-sm font-medium leading-none peer-disabled:cursor-not-allowed peer-disabled:opacity-70 cursor-pointer"
>
Allow network access
</label>
<p className="text-sm text-muted-foreground">
Makes the server accessible from other devices on your network. Restart the app
after changing this setting.
</p>
</div>
</div>
</div>
)}
</CardContent>
</Card>
);
@@ -0,0 +1,116 @@
import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/components/ui/card';
import { Checkbox } from '@/components/ui/checkbox';
import { Slider } from '@/components/ui/slider';
import { useServerStore } from '@/stores/serverStore';
export function GenerationSettings() {
const maxChunkChars = useServerStore((state) => state.maxChunkChars);
const setMaxChunkChars = useServerStore((state) => state.setMaxChunkChars);
const crossfadeMs = useServerStore((state) => state.crossfadeMs);
const setCrossfadeMs = useServerStore((state) => state.setCrossfadeMs);
const normalizeAudio = useServerStore((state) => state.normalizeAudio);
const setNormalizeAudio = useServerStore((state) => state.setNormalizeAudio);
const autoplayOnGenerate = useServerStore((state) => state.autoplayOnGenerate);
const setAutoplayOnGenerate = useServerStore((state) => state.setAutoplayOnGenerate);
return (
<Card role="region" aria-label="Generation Settings" tabIndex={0}>
<CardHeader>
<CardTitle>Generation Settings</CardTitle>
<CardDescription>
Controls for long text generation. These settings apply to all engines.
</CardDescription>
</CardHeader>
<CardContent>
<div className="space-y-6">
<div className="space-y-3">
<div className="flex items-center justify-between">
<label htmlFor="maxChunkChars" className="text-sm font-medium leading-none">
Auto-chunking limit
</label>
<span className="text-sm tabular-nums text-muted-foreground">
{maxChunkChars} chars
</span>
</div>
<Slider
id="maxChunkChars"
value={[maxChunkChars]}
onValueChange={([value]) => setMaxChunkChars(value)}
min={100}
max={5000}
step={50}
aria-label="Auto-chunking character limit"
/>
<p className="text-sm text-muted-foreground">
Long text is split into chunks at sentence boundaries before generating. Lower values
can improve quality for long outputs.
</p>
</div>
<div className="space-y-3">
<div className="flex items-center justify-between">
<label htmlFor="crossfadeMs" className="text-sm font-medium leading-none">
Chunk crossfade
</label>
<span className="text-sm tabular-nums text-muted-foreground">
{crossfadeMs === 0 ? 'Cut' : `${crossfadeMs}ms`}
</span>
</div>
<Slider
id="crossfadeMs"
value={[crossfadeMs]}
onValueChange={([value]) => setCrossfadeMs(value)}
min={0}
max={200}
step={10}
aria-label="Chunk crossfade duration"
/>
<p className="text-sm text-muted-foreground">
Blends audio between chunks to smooth transitions. Set to 0 for a hard cut.
</p>
</div>
<div className="flex items-start gap-3">
<Checkbox
id="normalizeAudio"
checked={normalizeAudio}
onCheckedChange={setNormalizeAudio}
className="mt-[6px]"
/>
<div className="space-y-1">
<label
htmlFor="normalizeAudio"
className="text-sm font-medium leading-none cursor-pointer"
>
Normalize audio
</label>
<p className="text-sm text-muted-foreground">
Adjusts output volume to a consistent level across generations.
</p>
</div>
</div>
<div className="flex items-start gap-3">
<Checkbox
id="autoplayOnGenerate"
checked={autoplayOnGenerate}
onCheckedChange={setAutoplayOnGenerate}
className="mt-[6px]"
/>
<div className="space-y-1">
<label
htmlFor="autoplayOnGenerate"
className="text-sm font-medium leading-none cursor-pointer"
>
Autoplay on generate
</label>
<p className="text-sm text-muted-foreground">
Automatically play audio when a generation completes.
</p>
</div>
</div>
</div>
</CardContent>
</Card>
);
}
@@ -0,0 +1,383 @@
import { useQuery, useQueryClient } from '@tanstack/react-query';
import { AlertCircle, Download, Loader2, RotateCw, Trash2 } from 'lucide-react';
import { useCallback, useEffect, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card';
import { Progress } from '@/components/ui/progress';
import { apiClient } from '@/lib/api/client';
import type { CudaDownloadProgress } from '@/lib/api/types';
import { useServerHealth } from '@/lib/hooks/useServer';
import { usePlatform } from '@/platform/PlatformContext';
import { useServerStore } from '@/stores/serverStore';
type RestartPhase = 'idle' | 'stopping' | 'waiting' | 'ready';
export function GpuAcceleration() {
const platform = usePlatform();
const queryClient = useQueryClient();
const serverUrl = useServerStore((state) => state.serverUrl);
const { data: health } = useServerHealth();
const [restartPhase, setRestartPhase] = useState<RestartPhase>('idle');
const [error, setError] = useState<string | null>(null);
const [downloadProgress, setDownloadProgress] = useState<CudaDownloadProgress | null>(null);
const healthPollRef = useRef<ReturnType<typeof setInterval> | null>(null);
// Query CUDA backend status
const {
data: cudaStatus,
isLoading: _cudaStatusLoading,
refetch: refetchCudaStatus,
} = useQuery({
queryKey: ['cuda-status', serverUrl],
queryFn: () => apiClient.getCudaStatus(),
refetchInterval: (query) => (query.state.status === 'pending' ? false : 10000),
retry: 1,
enabled: !!health, // Only fetch when backend is reachable
});
// Derived state
const isCurrentlyCuda = health?.backend_variant === 'cuda';
const cudaAvailable = cudaStatus?.available ?? false;
const cudaDownloading = cudaStatus?.downloading ?? false;
// Clean up health poll on unmount
useEffect(() => {
return () => {
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
};
}, []);
// SSE progress tracking during download
useEffect(() => {
if (!cudaDownloading || !serverUrl) {
return;
}
const eventSource = new EventSource(`${serverUrl}/backend/cuda-progress`);
eventSource.onmessage = (event) => {
try {
const data = JSON.parse(event.data) as CudaDownloadProgress;
setDownloadProgress(data);
if (data.status === 'complete') {
eventSource.close();
setDownloadProgress(null);
refetchCudaStatus();
} else if (data.status === 'error') {
eventSource.close();
setError(data.error || 'Download failed');
setDownloadProgress(null);
refetchCudaStatus();
}
} catch (e) {
console.error('Error parsing CUDA progress event:', e);
}
};
eventSource.onerror = () => {
eventSource.close();
};
return () => {
eventSource.close();
};
}, [cudaDownloading, serverUrl, refetchCudaStatus]);
// Start aggressive health polling during restart
const startHealthPolling = useCallback(() => {
if (healthPollRef.current) return;
healthPollRef.current = setInterval(async () => {
try {
const result = await apiClient.getHealth();
if (result.status === 'healthy') {
// Server is back up
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
setRestartPhase('ready');
// Invalidate all queries to refresh UI
queryClient.invalidateQueries();
// Reset after a moment
setTimeout(() => setRestartPhase('idle'), 2000);
}
} catch {
// Server still down, keep polling
}
}, 1000);
}, [queryClient]);
const handleDownload = async () => {
setError(null);
try {
await apiClient.downloadCudaBackend();
refetchCudaStatus();
} catch (e: unknown) {
const msg = e instanceof Error ? e.message : 'Failed to start download';
if (msg.includes('already downloaded')) {
refetchCudaStatus();
} else {
setError(msg);
}
}
};
const handleRestart = async () => {
setError(null);
setRestartPhase('stopping');
try {
setRestartPhase('waiting');
startHealthPolling();
await platform.lifecycle.restartServer();
// Invoke resolved — server is likely ready. Stop polling and refresh.
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
setRestartPhase('ready');
queryClient.invalidateQueries();
setTimeout(() => setRestartPhase('idle'), 2000);
} catch (e: unknown) {
setRestartPhase('idle');
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
setError(e instanceof Error ? e.message : 'Restart failed');
}
};
const handleSwitchToCpu = async () => {
// To switch to CPU: delete the CUDA binary, then restart.
// start_server always prefers CUDA if present, so we must remove it first.
setError(null);
setRestartPhase('stopping');
try {
await apiClient.deleteCudaBackend();
setRestartPhase('waiting');
startHealthPolling();
await platform.lifecycle.restartServer();
// Invoke resolved — server is likely ready
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
setRestartPhase('ready');
queryClient.invalidateQueries();
setTimeout(() => setRestartPhase('idle'), 2000);
} catch (e: unknown) {
setRestartPhase('idle');
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
setError(e instanceof Error ? e.message : 'Failed to switch to CPU');
refetchCudaStatus();
}
};
const handleDelete = async () => {
setError(null);
try {
await apiClient.deleteCudaBackend();
refetchCudaStatus();
} catch (e: unknown) {
setError(e instanceof Error ? e.message : 'Failed to delete CUDA backend');
}
};
const formatBytes = (bytes: number): string => {
if (bytes === 0) return '0 B';
const k = 1024;
const sizes = ['B', 'KB', 'MB', 'GB'];
const i = Math.floor(Math.log(bytes) / Math.log(k));
return `${(bytes / k ** i).toFixed(1)} ${sizes[i]}`;
};
// Don't render until health data is available
if (!health) return null;
// If the system already has native GPU (MPS, etc.), only show info - no CUDA needed
const hasNativeGpu =
health.gpu_available &&
!isCurrentlyCuda &&
health.gpu_type &&
!health.gpu_type.includes('CUDA');
return (
<Card>
<CardHeader>
<CardTitle>GPU Acceleration</CardTitle>
</CardHeader>
<CardContent className="space-y-4">
{/* GPU status */}
<div className="space-y-1">
{health.gpu_available && health.gpu_type ? (
<>
<div className="text-sm font-medium">
{health.gpu_type.replace(/^(CUDA|ROCm|MPS|Metal|XPU|DirectML)\s*\((.+)\)$/, '$2') ||
health.gpu_type}
</div>
<div className="text-sm text-muted-foreground">
{health.gpu_type.replace(/\s*\(.+\)$/, '')}
{health.vram_used_mb != null && health.vram_used_mb > 0
? ` \u00b7 ${health.vram_used_mb.toFixed(0)} MB VRAM used`
: ''}
</div>
</>
) : (
<>
<div className="text-sm font-medium">CPU</div>
<div className="text-sm text-muted-foreground">No GPU acceleration available</div>
</>
)}
</div>
{/* Native GPU detected - no CUDA download needed */}
{/* Currently running CUDA - show switch back to CPU */}
{isCurrentlyCuda && platform.metadata.isTauri && (
<>
{restartPhase !== 'idle' ? (
<div className="flex items-center gap-2 p-3 rounded-lg bg-primary/5 border">
<Loader2 className="h-4 w-4 animate-spin" />
<span className="text-sm">
{restartPhase === 'stopping' && 'Stopping server...'}
{restartPhase === 'waiting' && 'Restarting server...'}
{restartPhase === 'ready' && 'Server restarted successfully!'}
</span>
</div>
) : (
<div className="space-y-3">
<p className="text-sm text-muted-foreground">
Running with CUDA GPU acceleration. Switch back to CPU if needed (you can
re-download later).
</p>
<Button onClick={handleSwitchToCpu} variant="outline" className="w-full" size="sm">
<RotateCw className="h-4 w-4 mr-2" />
Switch to CPU Backend
</Button>
</div>
)}
{error && (
<div className="flex items-center gap-2 text-sm text-destructive">
<AlertCircle className="h-4 w-4 shrink-0" />
<span>{error}</span>
</div>
)}
</>
)}
{/* CUDA download/manage section - show when no native GPU and not currently running CUDA */}
{!hasNativeGpu && !isCurrentlyCuda && (
<>
{/* Download progress (manual download or auto-update) */}
{cudaDownloading && downloadProgress && (
<div className="space-y-2">
<div className="flex items-center justify-between text-sm">
<div className="flex items-center gap-2">
<Loader2 className="h-4 w-4 animate-spin" />
<span>
{downloadProgress.filename ||
(cudaAvailable
? 'Updating CUDA backend...'
: 'Downloading CUDA backend...')}
</span>
</div>
{downloadProgress.total > 0 && (
<span className="text-muted-foreground">
{downloadProgress.progress.toFixed(1)}%
</span>
)}
</div>
{downloadProgress.total > 0 && (
<>
<Progress value={downloadProgress.progress} className="h-2" />
<div className="text-xs text-muted-foreground">
{formatBytes(downloadProgress.current)} /{' '}
{formatBytes(downloadProgress.total)}
</div>
</>
)}
</div>
)}
{/* Restart in progress */}
{restartPhase !== 'idle' && (
<div className="flex items-center gap-2 p-3 rounded-lg bg-primary/5 border">
<Loader2 className="h-4 w-4 animate-spin" />
<span className="text-sm">
{restartPhase === 'stopping' && 'Stopping server...'}
{restartPhase === 'waiting' && 'Restarting server...'}
{restartPhase === 'ready' && 'Server restarted successfully!'}
</span>
</div>
)}
{/* Error display */}
{error && (
<div className="flex items-center gap-2 text-sm text-destructive">
<AlertCircle className="h-4 w-4 shrink-0" />
<span>{error}</span>
</div>
)}
{/* Actions */}
{restartPhase === 'idle' && !cudaDownloading && (
<div className="space-y-2">
{/* Not downloaded yet - show download button */}
{!cudaAvailable && (
<div className="space-y-3">
<p className="text-sm text-muted-foreground">
Download the CUDA backend (~2.4 GB) for NVIDIA GPU acceleration. Requires an
NVIDIA GPU with CUDA support.
</p>
<Button onClick={handleDownload} className="w-full" size="sm">
<Download className="h-4 w-4 mr-2" />
Download CUDA Backend
</Button>
</div>
)}
{/* Downloaded but not active - show switch button */}
{cudaAvailable && platform.metadata.isTauri && (
<div className="space-y-3">
<p className="text-sm text-muted-foreground">
CUDA backend is downloaded and ready. Restart the server to enable GPU
acceleration.
</p>
<Button onClick={handleRestart} className="w-full" size="sm">
<RotateCw className="h-4 w-4 mr-2" />
Switch to CUDA Backend
</Button>
</div>
)}
{/* Delete option when downloaded (and not active) */}
{cudaAvailable && (
<Button
onClick={handleDelete}
variant="ghost"
className="w-full text-muted-foreground hover:text-destructive"
size="sm"
>
<Trash2 className="h-4 w-4 mr-2" />
Remove CUDA Backend
</Button>
)}
</div>
)}
</>
)}
</CardContent>
</Card>
);
}
File diff suppressed because it is too large Load Diff
@@ -12,7 +12,11 @@ interface ModelProgressProps {
isDownloading?: boolean;
}
export function ModelProgress({ modelName, displayName, isDownloading = false }: ModelProgressProps) {
export function ModelProgress({
modelName,
displayName,
isDownloading = false,
}: ModelProgressProps) {
const [progress, setProgress] = useState<ModelProgressType | null>(null);
const serverUrl = useServerStore((state) => state.serverUrl);
@@ -3,14 +3,13 @@ import { Badge } from '@/components/ui/badge';
import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card';
import { useServerHealth } from '@/lib/hooks/useServer';
import { useServerStore } from '@/stores/serverStore';
import { ModelProgress } from './ModelProgress';
export function ServerStatus() {
const { data: health, isLoading, error } = useServerHealth();
const serverUrl = useServerStore((state) => state.serverUrl);
return (
<Card>
<Card role="region" aria-label="Server Status" tabIndex={0}>
<CardHeader>
<CardTitle>Server Status</CardTitle>
</CardHeader>
@@ -20,16 +19,6 @@ export function ServerStatus() {
<div className="font-mono text-sm">{serverUrl}</div>
</div>
{/* Model download progress */}
<div className="space-y-2">
<ModelProgress modelName="qwen-tts-1.7B" displayName="Qwen TTS 1.7B" />
<ModelProgress modelName="qwen-tts-0.6B" displayName="Qwen TTS 0.6B" />
<ModelProgress modelName="whisper-base" displayName="Whisper Base" />
<ModelProgress modelName="whisper-small" displayName="Whisper Small" />
<ModelProgress modelName="whisper-medium" displayName="Whisper Medium" />
<ModelProgress modelName="whisper-large" displayName="Whisper Large" />
</div>
{isLoading ? (
<div className="flex items-center gap-2">
<Loader2 className="h-4 w-4 animate-spin" />
@@ -11,6 +11,7 @@ export function UpdateStatus() {
const platform = usePlatform();
const { status, checkForUpdates, downloadAndInstall, restartAndInstall } = useAutoUpdater(false);
const [currentVersion, setCurrentVersion] = useState<string>('');
const isDev = !import.meta.env?.PROD;
useEffect(() => {
platform.metadata
@@ -20,7 +21,7 @@ export function UpdateStatus() {
}, [platform]);
return (
<Card>
<Card role="region" aria-label="App Updates" tabIndex={0}>
<CardHeader>
<CardTitle>App Updates</CardTitle>
</CardHeader>
@@ -28,97 +29,110 @@ export function UpdateStatus() {
<div className="flex items-center justify-between">
<div className="space-y-1">
<div className="text-sm font-medium">Current Version</div>
<div className="text-sm text-muted-foreground">v{currentVersion}</div>
<div className="text-sm text-muted-foreground">
v{currentVersion}
{isDev ? ' (dev)' : ''}
</div>
</div>
<Button
onClick={checkForUpdates}
disabled={status.checking || status.downloading || status.readyToInstall}
variant="outline"
size="sm"
>
<RefreshCw className={`h-4 w-4 mr-2 ${status.checking ? 'animate-spin' : ''}`} />
Check for Updates
</Button>
{!isDev && (
<Button
onClick={checkForUpdates}
disabled={status.checking || status.downloading || status.readyToInstall}
variant="outline"
size="sm"
>
<RefreshCw className={`h-4 w-4 mr-2 ${status.checking ? 'animate-spin' : ''}`} />
Check for Updates
</Button>
)}
</div>
{status.checking && (
<div className="flex items-center gap-2 text-sm text-muted-foreground">
<RefreshCw className="h-4 w-4 animate-spin" />
Checking for updates...
{isDev ? (
<div className="text-sm text-muted-foreground">
Auto-updates are disabled in development mode.
</div>
)}
{status.error && (
<div className="flex items-center gap-2 text-sm text-destructive">
<AlertCircle className="h-4 w-4" />
{status.error}
</div>
)}
{status.available && !status.downloading && !status.readyToInstall && (
<div className="space-y-3 p-4 border rounded-lg bg-primary/5">
<div className="flex items-center justify-between">
<div>
<div className="font-semibold">Update Available</div>
<div className="text-sm text-muted-foreground">Version {status.version}</div>
) : (
<>
{status.checking && (
<div className="flex items-center gap-2 text-sm text-muted-foreground">
<RefreshCw className="h-4 w-4 animate-spin" />
Checking for updates...
</div>
<Badge>New</Badge>
</div>
<Button onClick={downloadAndInstall} className="w-full" size="sm">
<Download className="h-4 w-4 mr-2" />
Download Update
</Button>
</div>
)}
)}
{status.downloading && (
<div className="space-y-2">
<div className="flex items-center justify-between text-sm">
<div className="flex items-center gap-2">
<Download className="h-4 w-4" />
Downloading update...
{status.error && (
<div className="flex items-center gap-2 text-sm text-destructive">
<AlertCircle className="h-4 w-4" />
{status.error}
</div>
{status.downloadProgress !== undefined && (
<span className="text-muted-foreground">{status.downloadProgress}%</span>
)}
</div>
<Progress value={status.downloadProgress} />
{status.downloadedBytes !== undefined &&
status.totalBytes !== undefined &&
status.totalBytes > 0 && (
<div className="text-xs text-muted-foreground">
{(status.downloadedBytes / 1024 / 1024).toFixed(1)} MB /{' '}
{(status.totalBytes / 1024 / 1024).toFixed(1)} MB
)}
{status.available && !status.downloading && !status.readyToInstall && (
<div className="space-y-3 p-4 border rounded-lg bg-primary/5">
<div className="flex items-center justify-between">
<div>
<div className="font-semibold">Update Available</div>
<div className="text-sm text-muted-foreground">Version {status.version}</div>
</div>
<Badge>New</Badge>
</div>
)}
</div>
)}
<Button onClick={downloadAndInstall} className="w-full" size="sm">
<Download className="h-4 w-4 mr-2" />
Download Update
</Button>
</div>
)}
{status.readyToInstall && (
<div className="space-y-3 p-4 border rounded-lg bg-accent/30 border-accent/50">
<div className="flex items-center gap-2">
<div>
<div className="font-semibold">Update Ready to Install</div>
{status.downloading && (
<div className="space-y-2">
<div className="flex items-center justify-between text-sm">
<div className="flex items-center gap-2">
<Download className="h-4 w-4" />
Downloading update...
</div>
{status.downloadProgress !== undefined && (
<span className="text-muted-foreground">{status.downloadProgress}%</span>
)}
</div>
<Progress value={status.downloadProgress} />
{status.downloadedBytes !== undefined &&
status.totalBytes !== undefined &&
status.totalBytes > 0 && (
<div className="text-xs text-muted-foreground">
{(status.downloadedBytes / 1024 / 1024).toFixed(1)} MB /{' '}
{(status.totalBytes / 1024 / 1024).toFixed(1)} MB
</div>
)}
</div>
)}
{status.readyToInstall && (
<div className="space-y-3 p-4 border rounded-lg bg-accent/30 border-accent/50">
<div className="flex items-center gap-2">
<div>
<div className="font-semibold">Update Ready to Install</div>
<div className="text-sm text-muted-foreground">
Version {status.version} has been downloaded
</div>
</div>
</div>
<div className="text-sm text-muted-foreground">
Version {status.version} has been downloaded
The app needs to restart to complete the installation. You can do this now or
later at your convenience.
</div>
<Button onClick={restartAndInstall} className="w-full" size="sm">
<RefreshCw className="h-4 w-4 mr-2" />
Restart Now
</Button>
</div>
</div>
<div className="text-sm text-muted-foreground">
The app needs to restart to complete the installation. You can do this now or later at
your convenience.
</div>
<Button onClick={restartAndInstall} className="w-full" size="sm">
<RefreshCw className="h-4 w-4 mr-2" />
Restart Now
</Button>
</div>
)}
)}
{!status.available && !status.checking && !status.error && status.checking === false && (
<div className="flex items-center gap-2 text-sm text-muted-foreground">
You're up to date
</div>
{!status.available && !status.checking && !status.error && (
<div className="flex items-center gap-2 text-sm text-muted-foreground">
You're up to date
</div>
)}
</>
)}
</CardContent>
</Card>
+135
View File
@@ -0,0 +1,135 @@
import { ArrowUpRight } from 'lucide-react';
import type { CSSProperties, ReactNode } from 'react';
import { useEffect, useState } from 'react';
import voiceboxLogo from '@/assets/voicebox-logo.png';
import { usePlatform } from '@/platform/PlatformContext';
function FadeIn({ delay = 0, children }: { delay?: number; children: ReactNode }) {
return (
<div
className="animate-[fadeInUp_0.5s_ease_both]"
style={{ animationDelay: `${delay}ms` } as CSSProperties}
>
{children}
</div>
);
}
export function AboutPage() {
const platform = usePlatform();
const [version, setVersion] = useState('');
useEffect(() => {
platform.metadata
.getVersion()
.then(setVersion)
.catch(() => setVersion(''));
}, [platform]);
return (
<>
<style>{`
@keyframes fadeInUp {
from {
opacity: 0;
transform: translateY(8px);
}
to {
opacity: 1;
transform: translateY(0);
}
}
`}</style>
<div className="max-w-md mx-auto h-full flex items-center">
<div className="flex flex-col items-center text-center space-y-5">
<FadeIn delay={0}>
<img src={voiceboxLogo} alt="Voicebox" className="w-20 h-20 object-contain" />
</FadeIn>
<FadeIn delay={80}>
<div className="space-y-1.5">
<h1 className="text-lg font-semibold">Voicebox</h1>
<p className="text-xs text-muted-foreground/60 h-4">
{version ? `v${version}` : '\u00A0'}
</p>
</div>
</FadeIn>
<FadeIn delay={160}>
<p className="text-sm text-muted-foreground leading-relaxed max-w-sm">
The open-source voice synthesis studio. Clone voices, generate speech, apply effects,
and build voice-powered apps — all running locally on your machine.
</p>
</FadeIn>
<FadeIn delay={240}>
<div className="flex items-center gap-1.5 text-sm text-muted-foreground">
<span>Created by</span>
<a
href="https://github.com/jamiepine"
target="_blank"
rel="noopener noreferrer"
className="text-accent hover:underline"
>
Jamie Pine
</a>
</div>
</FadeIn>
<FadeIn delay={320}>
<div className="flex flex-wrap justify-center gap-3 pt-2">
<a
href="https://buymeacoffee.com/jamiepine"
target="_blank"
rel="noopener noreferrer"
className="group inline-flex items-center gap-2 rounded-lg border border-border/60 px-4 py-2 text-sm transition-colors hover:bg-muted/50"
>
<svg
className="h-4 w-4 text-[#FFDD00]"
viewBox="0 0 24 24"
fill="currentColor"
aria-hidden="true"
>
<path d="m20.216 6.415-.132-.666c-.119-.598-.388-1.163-1.001-1.379-.197-.069-.42-.098-.57-.241-.152-.143-.196-.366-.231-.572-.065-.378-.125-.756-.192-1.133-.057-.325-.102-.69-.25-.987-.195-.4-.597-.634-.996-.788a5.723 5.723 0 0 0-.626-.194c-1-.263-2.05-.36-3.077-.416a25.834 25.834 0 0 0-3.7.062c-.915.083-1.88.184-2.75.5-.318.116-.646.256-.888.501-.297.302-.393.77-.177 1.146.154.267.415.456.692.58.36.162.737.284 1.123.366 1.075.238 2.189.331 3.287.37 1.218.05 2.437.01 3.65-.118.299-.033.598-.073.896-.119.352-.054.578-.513.474-.834-.124-.383-.457-.531-.834-.473-.466.074-.96.108-1.382.146-1.177.08-2.358.082-3.536.006a22.228 22.228 0 0 1-1.157-.107c-.086-.01-.18-.025-.258-.036-.243-.036-.484-.08-.724-.13-.111-.027-.111-.185 0-.212h.005c.277-.06.557-.108.838-.147h.002c.131-.009.263-.032.394-.048a25.076 25.076 0 0 1 3.426-.12c.674.019 1.347.067 2.017.144l.228.031c.267.04.533.088.798.145.392.085.895.113 1.07.542.055.137.08.288.111.431l.319 1.484a.237.237 0 0 1-.199.284h-.003c-.037.006-.075.01-.112.015a36.704 36.704 0 0 1-4.743.295 37.059 37.059 0 0 1-4.699-.304c-.14-.017-.293-.042-.417-.06-.326-.048-.649-.108-.973-.161-.393-.065-.768-.032-1.123.161-.29.16-.527.404-.675.701-.154.316-.199.66-.267 1-.069.34-.176.707-.135 1.056.087.753.613 1.365 1.37 1.502a39.69 39.69 0 0 0 11.343.376.483.483 0 0 1 .535.53l-.071.697-1.018 9.907c-.041.41-.047.832-.125 1.237-.122.637-.553 1.028-1.182 1.171-.577.131-1.165.2-1.756.205-.656.004-1.31-.025-1.966-.022-.699.004-1.556-.06-2.095-.58-.475-.458-.54-1.174-.605-1.793l-.731-7.013-.322-3.094c-.037-.351-.286-.695-.678-.678-.336.015-.718.3-.678.679l.228 2.185.949 9.112c.147 1.344 1.174 2.068 2.446 2.272.742.12 1.503.144 2.257.156.966.016 1.942.053 2.892-.122 1.408-.258 2.465-1.198 2.616-2.657.34-3.332.683-6.663 1.024-9.995l.215-2.087a.484.484 0 0 1 .39-.426c.402-.078.787-.212 1.074-.518.455-.488.546-1.124.385-1.766zm-1.478.772c-.145.137-.363.201-.578.233-2.416.359-4.866.54-7.308.46-1.748-.06-3.477-.254-5.207-.498-.17-.024-.353-.055-.47-.18-.22-.236-.111-.71-.054-.995.052-.26.152-.609.463-.646.484-.057 1.046.148 1.526.22.577.088 1.156.159 1.737.212 2.48.226 5.002.19 7.472-.14.45-.06.899-.13 1.345-.21.399-.072.84-.206 1.08.206.166.281.188.657.162.974a.544.544 0 0 1-.169.364zm-6.159 3.9c-.862.37-1.84.788-3.109.788a5.884 5.884 0 0 1-1.569-.217l.877 9.004c.065.78.717 1.38 1.5 1.38 0 0 1.243.065 1.658.065.447 0 1.786-.065 1.786-.065.783 0 1.434-.6 1.499-1.38l.94-9.95a3.996 3.996 0 0 0-1.322-.238c-.826 0-1.491.284-2.26.613z" />
</svg>
Buy me a coffee
<ArrowUpRight className="h-3.5 w-3.5 text-muted-foreground/40 group-hover:text-muted-foreground transition-colors" />
</a>
<a
href="https://github.com/jamiepine/voicebox"
target="_blank"
rel="noopener noreferrer"
className="group inline-flex items-center gap-2 rounded-lg border border-border/60 px-4 py-2 text-sm transition-colors hover:bg-muted/50"
>
<svg
className="h-4 w-4 text-muted-foreground"
viewBox="0 0 24 24"
fill="currentColor"
aria-hidden="true"
>
<path d="M12 2C6.477 2 2 6.484 2 12.017c0 4.425 2.865 8.18 6.839 9.504.5.092.682-.217.682-.483 0-.237-.008-.868-.013-1.703-2.782.605-3.369-1.343-3.369-1.343-.454-1.158-1.11-1.466-1.11-1.466-.908-.62.069-.608.069-.608 1.003.07 1.531 1.032 1.531 1.032.892 1.53 2.341 1.088 2.91.832.092-.647.35-1.088.636-1.338-2.22-.253-4.555-1.113-4.555-4.951 0-1.093.39-1.988 1.029-2.688-.103-.253-.446-1.272.098-2.65 0 0 .84-.27 2.75 1.026A9.564 9.564 0 0112 6.844c.85.004 1.705.115 2.504.337 1.909-1.296 2.747-1.027 2.747-1.027.546 1.379.202 2.398.1 2.651.64.7 1.028 1.595 1.028 2.688 0 3.848-2.339 4.695-4.566 4.943.359.309.678.92.678 1.855 0 1.338-.012 2.419-.012 2.747 0 .268.18.58.688.482A10.019 10.019 0 0022 12.017C22 6.484 17.522 2 12 2z" />
</svg>
GitHub
<ArrowUpRight className="h-3.5 w-3.5 text-muted-foreground/40 group-hover:text-muted-foreground transition-colors" />
</a>
</div>
</FadeIn>
<FadeIn delay={400}>
<p className="text-xs text-muted-foreground/40 pt-4">
Licensed under{' '}
<a
href="https://github.com/jamiepine/voicebox/blob/main/LICENSE"
target="_blank"
rel="noopener noreferrer"
className="hover:text-muted-foreground/60 transition-colors"
>
MIT
</a>
</p>
</FadeIn>
</div>
</div>
</>
);
}
@@ -0,0 +1,220 @@
import changelogRaw from 'virtual:changelog';
import { useMemo, useState } from 'react';
import { Badge } from '@/components/ui/badge';
import { type ChangelogEntry, parseChangelog } from '@/lib/utils/parseChangelog';
function renderMarkdown(md: string): React.ReactNode[] {
const lines = md.split('\n');
const elements: React.ReactNode[] = [];
let i = 0;
while (i < lines.length) {
const line = lines[i];
// Skip empty lines
if (line.trim() === '') {
i++;
continue;
}
// Tables — collect all lines starting with |
if (line.trim().startsWith('|')) {
const tableLines: string[] = [];
while (i < lines.length && lines[i].trim().startsWith('|')) {
tableLines.push(lines[i]);
i++;
}
elements.push(renderTable(tableLines, elements.length));
continue;
}
// Headings
if (line.startsWith('#### ')) {
elements.push(
<h5 key={elements.length} className="text-sm font-medium mt-5 mb-1">
{inlineMarkdown(line.slice(5))}
</h5>,
);
i++;
continue;
}
if (line.startsWith('### ')) {
elements.push(
<h4 key={elements.length} className="text-sm font-medium mt-6 mb-2">
{inlineMarkdown(line.slice(4))}
</h4>,
);
i++;
continue;
}
// List items — collect consecutive
if (line.startsWith('- ')) {
const items: string[] = [];
while (i < lines.length && lines[i].startsWith('- ')) {
items.push(lines[i].slice(2));
i++;
}
elements.push(
<ul key={elements.length} className="space-y-1 my-2">
{items.map((item, idx) => (
<li key={idx} className="text-sm text-muted-foreground flex gap-2">
<span className="text-muted-foreground/50 select-none shrink-0">&bull;</span>
<span>{inlineMarkdown(item)}</span>
</li>
))}
</ul>,
);
continue;
}
// Paragraph
elements.push(
<p key={elements.length} className="text-sm text-muted-foreground my-2">
{inlineMarkdown(line)}
</p>,
);
i++;
}
return elements;
}
function renderTable(tableLines: string[], keyBase: number): React.ReactNode {
const parseRow = (line: string) =>
line
.split('|')
.slice(1, -1)
.map((c) => c.trim());
const headers = parseRow(tableLines[0]);
// Skip separator line (index 1)
const rows = tableLines.slice(2).map(parseRow);
return (
<div key={keyBase} className="overflow-x-auto my-3">
<table className="text-sm w-full">
<thead>
<tr className="border-b">
{headers.map((h, hIdx) => (
<th
key={hIdx}
className="text-left py-1.5 pr-4 text-muted-foreground font-medium text-xs"
>
{inlineMarkdown(h)}
</th>
))}
</tr>
</thead>
<tbody>
{rows.map((row, rowIdx) => (
<tr key={rowIdx} className="border-b border-border/50">
{row.map((cell, cellIdx) => (
<td key={cellIdx} className="py-1.5 pr-4 text-muted-foreground">
{inlineMarkdown(cell)}
</td>
))}
</tr>
))}
</tbody>
</table>
</div>
);
}
function inlineMarkdown(text: string): React.ReactNode {
// Process inline markdown: bold, code, links
const parts: React.ReactNode[] = [];
// Regex matches: **bold**, `code`, [text](url)
const inlineRe = /\*\*(.+?)\*\*|`([^`]+)`|\[([^\]]+)\]\(([^)]+)\)/g;
let lastIndex = 0;
let match: RegExpExecArray | null = inlineRe.exec(text);
while (match !== null) {
if (match.index > lastIndex) {
parts.push(text.slice(lastIndex, match.index));
}
if (match[1] !== undefined) {
// Bold
parts.push(
<strong key={parts.length} className="font-medium text-foreground">
{match[1]}
</strong>,
);
} else if (match[2] !== undefined) {
// Code
parts.push(
<code key={parts.length} className="px-1 py-0.5 rounded bg-muted text-xs font-mono">
{match[2]}
</code>,
);
} else if (match[3] !== undefined && match[4] !== undefined) {
// Link
parts.push(
<a
key={parts.length}
href={match[4]}
target="_blank"
rel="noopener noreferrer"
className="text-accent hover:underline"
>
{match[3]}
</a>,
);
}
lastIndex = match.index + match[0].length;
match = inlineRe.exec(text);
}
if (lastIndex < text.length) {
parts.push(text.slice(lastIndex));
}
return parts.length === 1 ? parts[0] : parts;
}
function ChangelogEntryCard({ entry }: { entry: ChangelogEntry }) {
const [expanded, setExpanded] = useState(false);
const content = useMemo(() => renderMarkdown(entry.body), [entry.body]);
const isLong = entry.body.split('\n').length > 12;
return (
<div className="border-b border-border/50 pb-6">
<div className="flex items-baseline gap-3 mb-3">
<h3 className="text-xl font-semibold tracking-tight">{entry.version}</h3>
{entry.date && <span className="text-xs text-muted-foreground">{entry.date}</span>}
{entry.version === 'Unreleased' && <Badge variant="outline">dev</Badge>}
</div>
<div className={isLong && !expanded ? 'max-h-48 overflow-hidden relative' : ''}>
{content}
{isLong && !expanded && (
<div className="absolute bottom-0 left-0 right-0 h-16 bg-gradient-to-t from-background to-transparent" />
)}
</div>
{isLong && (
<button
onClick={() => setExpanded(!expanded)}
className="text-xs text-accent hover:underline mt-2"
>
{expanded ? 'Show less' : 'Show more'}
</button>
)}
</div>
);
}
export function ChangelogPage() {
const entries = useMemo(() => parseChangelog(changelogRaw), []);
return (
<div className="space-y-6 max-w-2xl">
{entries.map((entry) => (
<ChangelogEntryCard key={entry.version} entry={entry} />
))}
</div>
);
}
@@ -0,0 +1,379 @@
import { zodResolver } from '@hookform/resolvers/zod';
import { AlertCircle, ArrowUpRight, Book, Download, Loader2, RefreshCw } from 'lucide-react';
import { useEffect, useState } from 'react';
import { useForm } from 'react-hook-form';
import * as z from 'zod';
import { Button } from '@/components/ui/button';
import { Form, FormControl, FormField, FormItem, FormMessage } from '@/components/ui/form';
import { Input } from '@/components/ui/input';
import { Progress } from '@/components/ui/progress';
import { Toggle } from '@/components/ui/toggle';
import { useToast } from '@/components/ui/use-toast';
import { useAutoUpdater } from '@/hooks/useAutoUpdater';
import { useServerHealth } from '@/lib/hooks/useServer';
import { usePlatform } from '@/platform/PlatformContext';
import { useServerStore } from '@/stores/serverStore';
import { SettingRow, SettingSection } from './SettingRow';
const connectionSchema = z.object({
serverUrl: z.string().url('Please enter a valid URL'),
});
type ConnectionFormValues = z.infer<typeof connectionSchema>;
export function GeneralPage() {
const platform = usePlatform();
const serverUrl = useServerStore((state) => state.serverUrl);
const setServerUrl = useServerStore((state) => state.setServerUrl);
const keepServerRunningOnClose = useServerStore((state) => state.keepServerRunningOnClose);
const setKeepServerRunningOnClose = useServerStore((state) => state.setKeepServerRunningOnClose);
const mode = useServerStore((state) => state.mode);
const setMode = useServerStore((state) => state.setMode);
const { toast } = useToast();
const { data: health, isLoading, error: healthError } = useServerHealth();
const form = useForm<ConnectionFormValues>({
resolver: zodResolver(connectionSchema),
defaultValues: { serverUrl },
});
useEffect(() => {
form.reset({ serverUrl });
}, [serverUrl, form]);
const { isDirty } = form.formState;
function onSubmit(data: ConnectionFormValues) {
setServerUrl(data.serverUrl);
form.reset(data);
toast({
title: 'Server URL updated',
description: `Connected to ${data.serverUrl}`,
});
}
return (
<div className="space-y-8 max-w-2xl">
<div className="grid grid-cols-2 gap-3">
<a
href="https://docs.voicebox.sh"
target="_blank"
rel="noopener noreferrer"
className="group flex items-center gap-3 rounded-lg border border-border/60 p-4 transition-colors hover:bg-muted/50"
>
<Book className="h-5 w-5 shrink-0 text-accent" strokeWidth={2.5} />
<div className="min-w-0 flex-1">
<div className="text-sm font-medium">Read the Docs</div>
<div className="text-xs text-muted-foreground">docs.voicebox.sh</div>
</div>
<ArrowUpRight className="h-4 w-4 text-muted-foreground/40 group-hover:text-muted-foreground transition-colors" />
</a>
<a
href="https://discord.gg/StkzQasqPS"
target="_blank"
rel="noopener noreferrer"
className="group flex items-center gap-3 rounded-lg border border-border/60 p-4 transition-colors hover:bg-muted/50"
>
<svg
className="h-5 w-5 shrink-0 text-accent"
viewBox="0 0 24 24"
fill="currentColor"
aria-hidden="true"
>
<path d="M20.317 4.37a19.791 19.791 0 0 0-4.885-1.515.074.074 0 0 0-.079.037c-.21.375-.444.864-.608 1.25a18.27 18.27 0 0 0-5.487 0 12.64 12.64 0 0 0-.617-1.25.077.077 0 0 0-.079-.037A19.736 19.736 0 0 0 3.677 4.37a.07.07 0 0 0-.032.027C.533 9.046-.32 13.58.099 18.057a.082.082 0 0 0 .031.057 19.9 19.9 0 0 0 5.993 3.03.078.078 0 0 0 .084-.028c.462-.63.874-1.295 1.226-1.994a.076.076 0 0 0-.041-.106 13.107 13.107 0 0 1-1.872-.892.077.077 0 0 1-.008-.128 10.2 10.2 0 0 0 .372-.292.074.074 0 0 1 .077-.01c3.928 1.793 8.18 1.793 12.062 0a.074.074 0 0 1 .078.01c.12.098.246.198.373.292a.077.077 0 0 1-.006.127 12.299 12.299 0 0 1-1.873.892.077.077 0 0 0-.041.107c.36.698.772 1.362 1.225 1.993a.076.076 0 0 0 .084.028 19.839 19.839 0 0 0 6.002-3.03.077.077 0 0 0 .032-.054c.5-5.177-.838-9.674-3.549-13.66a.061.061 0 0 0-.031-.03zM8.02 15.33c-1.183 0-2.157-1.085-2.157-2.419 0-1.333.956-2.419 2.157-2.419 1.21 0 2.176 1.095 2.157 2.42 0 1.333-.956 2.418-2.157 2.418zm7.975 0c-1.183 0-2.157-1.085-2.157-2.419 0-1.333.955-2.419 2.157-2.419 1.21 0 2.176 1.095 2.157 2.42 0 1.333-.946 2.418-2.157 2.418z" />
</svg>
<div className="min-w-0 flex-1">
<div className="text-sm font-medium">Join the Discord</div>
<div className="text-xs text-muted-foreground">Get help & share voices</div>
</div>
<ArrowUpRight className="h-4 w-4 text-muted-foreground/40 group-hover:text-muted-foreground transition-colors" />
</a>
</div>
<SettingSection>
<SettingRow
title="Server URL"
description="The address of your voicebox backend server."
action={
<ConnectionStatus health={health} isLoading={isLoading} healthError={healthError} />
}
>
<Form {...form}>
<form onSubmit={form.handleSubmit(onSubmit)} className="flex gap-2">
<FormField
control={form.control}
name="serverUrl"
render={({ field }) => (
<FormItem className="flex-1">
<FormControl>
<Input placeholder="http://127.0.0.1:17493" {...field} />
</FormControl>
<FormMessage />
</FormItem>
)}
/>
{isDirty && (
<Button type="submit" size="sm">
Save
</Button>
)}
</form>
</Form>
</SettingRow>
<SettingRow
title="Keep server running when app closes"
description="The server will continue running in the background after closing the app."
htmlFor="keepServerRunning"
action={
<Toggle
id="keepServerRunning"
checked={keepServerRunningOnClose}
onCheckedChange={(checked: boolean) => {
setKeepServerRunningOnClose(checked);
platform.lifecycle.setKeepServerRunning(checked).catch((error) => {
console.error('Failed to sync setting to Rust:', error);
setKeepServerRunningOnClose(!checked);
toast({
title: 'Failed to update setting',
description: 'Could not sync setting to backend.',
variant: 'destructive',
});
return;
});
toast({
title: 'Setting updated',
description: checked
? 'Server will continue running when app closes'
: 'Server will stop when app closes',
});
}}
/>
}
/>
{platform.metadata.isTauri && (
<SettingRow
title="Allow network access"
description="Makes the server accessible from other devices on your network. Restart the app after changing."
htmlFor="allowNetworkAccess"
action={
<Toggle
id="allowNetworkAccess"
checked={mode === 'remote'}
onCheckedChange={(checked: boolean) => {
setMode(checked ? 'remote' : 'local');
toast({
title: 'Setting updated',
description: checked
? 'Network access enabled. Restart the app to apply.'
: 'Network access disabled. Restart the app to apply.',
});
}}
/>
}
/>
)}
</SettingSection>
<ApiReferenceCard serverUrl={serverUrl} />
{platform.metadata.isTauri && <UpdatesSection />}
</div>
);
}
function ConnectionStatus({
health,
isLoading,
healthError,
}: {
health: ReturnType<typeof useServerHealth>['data'];
isLoading: boolean;
healthError: ReturnType<typeof useServerHealth>['error'];
}) {
if (isLoading) {
return (
<div className="flex items-center gap-2 rounded-full border border-border/60 px-3 py-1">
<Loader2 className="h-3 w-3 animate-spin text-muted-foreground" />
<span className="text-xs text-muted-foreground">Connecting</span>
</div>
);
}
if (healthError) {
return (
<div className="flex items-center gap-2 rounded-full border border-destructive/30 px-3 py-1">
<span className="relative flex h-2 w-2">
<span className="absolute inline-flex h-full w-full rounded-full bg-destructive/40" />
<span className="relative inline-flex h-2 w-2 rounded-full bg-destructive" />
</span>
<span className="text-xs text-destructive">Offline</span>
</div>
);
}
if (health) {
return (
<div className="flex items-center gap-2 rounded-full border border-accent/30 px-3 py-1">
<span className="relative flex h-2 w-2">
<span className="absolute inline-flex h-full w-full animate-ping rounded-full bg-accent/60" />
<span className="relative inline-flex h-2 w-2 rounded-full bg-accent shadow-[0_0_6px_1px_hsl(var(--accent)/0.5)]" />
</span>
<span className="text-xs text-muted-foreground">Online</span>
</div>
);
}
return null;
}
function UpdatesSection() {
const platform = usePlatform();
const { status, checkForUpdates, downloadAndInstall, restartAndInstall } = useAutoUpdater(false);
const [currentVersion, setCurrentVersion] = useState<string>('');
const isDev = !import.meta.env?.PROD;
useEffect(() => {
platform.metadata
.getVersion()
.then(setCurrentVersion)
.catch(() => setCurrentVersion('Unknown'));
}, [platform]);
return (
<SettingSection title="App Updates" description={`v${currentVersion}${isDev ? ' (dev)' : ''}`}>
{isDev ? (
<SettingRow
title="Development mode"
description="Auto-updates are disabled in development mode."
/>
) : (
<>
<SettingRow
title="Check for updates"
description={
status.available
? `Version ${status.version} available`
: status.checking
? 'Checking...'
: "You're up to date"
}
action={
<Button
onClick={checkForUpdates}
disabled={status.checking || status.downloading || status.readyToInstall}
variant="outline"
size="sm"
>
<RefreshCw
className={`h-3.5 w-3.5 mr-1.5 ${status.checking ? 'animate-spin' : ''}`}
/>
Check
</Button>
}
/>
{status.error && (
<SettingRow title="Update error">
<div className="flex items-center gap-2 text-sm text-destructive">
<AlertCircle className="h-4 w-4" />
{status.error}
</div>
</SettingRow>
)}
{status.available && !status.downloading && !status.readyToInstall && (
<SettingRow
title={`Update to ${status.version}`}
description="Download and install the latest version."
action={
<Button onClick={downloadAndInstall} size="sm">
<Download className="h-3.5 w-3.5 mr-1.5" />
Download
</Button>
}
/>
)}
{status.downloading && (
<SettingRow title="Downloading update...">
<div className="space-y-1.5">
<Progress value={status.downloadProgress} />
<div className="flex items-center justify-between text-xs text-muted-foreground">
{status.downloadedBytes !== undefined &&
status.totalBytes !== undefined &&
status.totalBytes > 0 ? (
<span>
{(status.downloadedBytes / 1024 / 1024).toFixed(1)} MB /{' '}
{(status.totalBytes / 1024 / 1024).toFixed(1)} MB
</span>
) : (
<span />
)}
{status.downloadProgress !== undefined && <span>{status.downloadProgress}%</span>}
</div>
</div>
</SettingRow>
)}
{status.readyToInstall && (
<SettingRow
title="Update ready to install"
description={`Version ${status.version} has been downloaded. Restart to complete.`}
action={
<Button onClick={restartAndInstall} size="sm">
<RefreshCw className="h-3.5 w-3.5 mr-1.5" />
Restart Now
</Button>
}
/>
)}
</>
)}
</SettingSection>
);
}
const API_ENDPOINTS = [
{ method: 'POST', path: '/generate', label: 'Generate speech' },
{ method: 'GET', path: '/health', label: 'Server status' },
{ method: 'GET', path: '/profiles', label: 'List voices' },
{ method: 'GET', path: '/history', label: 'Past generations' },
];
function ApiReferenceCard({ serverUrl }: { serverUrl: string }) {
return (
<div className="rounded-lg border border-border/60 p-4 space-y-3">
<div>
<h3 className="text-sm font-medium">API Access</h3>
<p className="text-sm text-muted-foreground">
Integrate Voicebox into your workflow via the REST API at{' '}
<code className="text-xs bg-muted px-1 py-0.5 rounded font-mono">{serverUrl}</code>
</p>
</div>
<div className="space-y-1">
{API_ENDPOINTS.map((ep) => (
<div key={ep.path} className="flex items-center gap-2.5 py-1">
<span
className={`text-[10px] font-mono font-semibold w-9 text-center rounded px-1 py-px ${
ep.method === 'POST' ? 'bg-accent/10 text-accent' : 'bg-muted text-muted-foreground'
}`}
>
{ep.method}
</span>
<code className="text-xs font-mono text-muted-foreground">{ep.path}</code>
<span className="text-xs text-muted-foreground/50 ml-auto">{ep.label}</span>
</div>
))}
</div>
<p className="text-xs text-muted-foreground">
<a
href={`${serverUrl}/docs`}
target="_blank"
rel="noopener noreferrer"
className="text-accent hover:underline"
>
View the full API reference
</a>
</p>
</div>
);
}
@@ -0,0 +1,138 @@
import { FolderOpen } from 'lucide-react';
import { useCallback, useEffect, useState } from 'react';
import { Button } from '@/components/ui/button';
import { Slider } from '@/components/ui/slider';
import { Toggle } from '@/components/ui/toggle';
import { usePlatform } from '@/platform/PlatformContext';
import { useServerStore } from '@/stores/serverStore';
import { SettingRow, SettingSection } from './SettingRow';
export function GenerationPage() {
const platform = usePlatform();
const serverUrl = useServerStore((state) => state.serverUrl);
const maxChunkChars = useServerStore((state) => state.maxChunkChars);
const setMaxChunkChars = useServerStore((state) => state.setMaxChunkChars);
const crossfadeMs = useServerStore((state) => state.crossfadeMs);
const setCrossfadeMs = useServerStore((state) => state.setCrossfadeMs);
const normalizeAudio = useServerStore((state) => state.normalizeAudio);
const setNormalizeAudio = useServerStore((state) => state.setNormalizeAudio);
const autoplayOnGenerate = useServerStore((state) => state.autoplayOnGenerate);
const setAutoplayOnGenerate = useServerStore((state) => state.setAutoplayOnGenerate);
const [opening, setOpening] = useState(false);
const [generationsPath, setGenerationsPath] = useState<string | null>(null);
useEffect(() => {
fetch(`${serverUrl}/health/filesystem`)
.then((res) => res.json())
.then((data) => {
const genDir = data.directories?.find((d: { path: string }) =>
d.path.includes('generations'),
);
if (genDir?.path) setGenerationsPath(genDir.path);
})
.catch(() => {});
}, [serverUrl]);
const openGenerationsFolder = useCallback(async () => {
if (!generationsPath) return;
setOpening(true);
try {
await platform.filesystem.openPath(generationsPath);
} catch (e) {
console.error('Failed to open generations folder:', e);
} finally {
setOpening(false);
}
}, [platform, generationsPath]);
return (
<div className="space-y-8 max-w-2xl">
<SettingSection
title="Generation"
description="Controls for long text generation. These settings apply to all engines."
>
<SettingRow
title="Auto-chunking limit"
description="Long text is split into chunks at sentence boundaries. Lower values can improve quality for long outputs."
action={
<span className="text-sm tabular-nums text-muted-foreground">
{maxChunkChars} chars
</span>
}
>
<Slider
id="maxChunkChars"
value={[maxChunkChars]}
onValueChange={([value]) => setMaxChunkChars(value)}
min={100}
max={5000}
step={50}
aria-label="Auto-chunking character limit"
/>
</SettingRow>
<SettingRow
title="Chunk crossfade"
description="Blends audio between chunks to smooth transitions. Set to 0 for a hard cut."
action={
<span className="text-sm tabular-nums text-muted-foreground">
{crossfadeMs === 0 ? 'Cut' : `${crossfadeMs}ms`}
</span>
}
>
<Slider
id="crossfadeMs"
value={[crossfadeMs]}
onValueChange={([value]) => setCrossfadeMs(value)}
min={0}
max={200}
step={10}
aria-label="Chunk crossfade duration"
/>
</SettingRow>
<SettingRow
title="Normalize audio"
description="Adjusts output volume to a consistent level across generations."
htmlFor="normalizeAudio"
action={
<Toggle
id="normalizeAudio"
checked={normalizeAudio}
onCheckedChange={setNormalizeAudio}
/>
}
/>
<SettingRow
title="Autoplay on generate"
description="Automatically play audio when a generation completes."
htmlFor="autoplayOnGenerate"
action={
<Toggle
id="autoplayOnGenerate"
checked={autoplayOnGenerate}
onCheckedChange={setAutoplayOnGenerate}
/>
}
/>
<SettingRow
title="Generations folder"
description={generationsPath ?? 'Where generated audio files are stored on disk.'}
action={
<Button
variant="outline"
size="sm"
onClick={openGenerationsFolder}
disabled={opening || !generationsPath}
>
<FolderOpen className="h-3.5 w-3.5 mr-1.5" />
Open
</Button>
}
/>
</SettingSection>
</div>
);
}
+405
View File
@@ -0,0 +1,405 @@
import { useQuery, useQueryClient } from '@tanstack/react-query';
import { AlertCircle, Cpu, Download, Loader2, RotateCw, Trash2 } from 'lucide-react';
import { useCallback, useEffect, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import { Progress } from '@/components/ui/progress';
import { apiClient } from '@/lib/api/client';
import type { CudaDownloadProgress, HealthResponse } from '@/lib/api/types';
import { useServerHealth } from '@/lib/hooks/useServer';
import { usePlatform } from '@/platform/PlatformContext';
import { useServerStore } from '@/stores/serverStore';
import { SettingRow, SettingSection } from './SettingRow';
type RestartPhase = 'idle' | 'stopping' | 'waiting' | 'ready';
function AppleLogo({ className }: { className?: string }) {
return (
<svg className={className} viewBox="0 0 24 24" fill="currentColor" aria-hidden="true">
<path d="M18.71 19.5c-.83 1.24-1.71 2.45-3.05 2.47-1.34.03-1.77-.79-3.29-.79-1.53 0-2 .77-3.27.82-1.31.05-2.3-1.32-3.14-2.53C4.25 17 2.94 12.45 4.7 9.39c.87-1.52 2.43-2.48 4.12-2.51 1.28-.02 2.5.87 3.29.87.78 0 2.26-1.07 3.8-.91.65.03 2.47.26 3.64 1.98-.09.06-2.17 1.28-2.15 3.81.03 3.02 2.65 4.03 2.68 4.04-.03.07-.42 1.44-1.38 2.83M13 3.5c.73-.83 1.94-1.46 2.94-1.5.13 1.17-.34 2.35-1.04 3.19-.69.85-1.83 1.51-2.95 1.42-.15-1.15.41-2.35 1.05-3.11z" />
</svg>
);
}
function GpuIcon({ className }: { className?: string }) {
return (
<svg
className={className}
viewBox="0 0 24 24"
fill="none"
stroke="currentColor"
strokeWidth="1.5"
strokeLinecap="round"
strokeLinejoin="round"
aria-hidden="true"
>
<rect x="4" y="6" width="16" height="12" rx="2" />
<path d="M2 10h2M2 14h2M20 10h2M20 14h2" />
<path d="M9 10h6M9 14h4" />
</svg>
);
}
function GpuInfoCard({ health }: { health: HealthResponse }) {
const hasGpu = health.gpu_available && health.gpu_type;
// Parse GPU name from type string like "CUDA (NVIDIA RTX 4090)" or "MPS (Apple M2 Pro)"
const gpuName = hasGpu
? health.gpu_type!.replace(/^(CUDA|ROCm|MPS|Metal|XPU|DirectML)\s*\((.+)\)$/, '$2') ||
health.gpu_type!
: null;
const gpuBackend = hasGpu ? health.gpu_type!.replace(/\s*\(.+\)$/, '') : null;
const isApple = gpuBackend === 'MPS' || gpuBackend === 'Metal';
const showBackendVariant = health.backend_variant && health.backend_variant !== 'cpu';
return (
<div className="rounded-lg border border-border/60 p-4">
<div className="flex items-center gap-3">
{hasGpu ? (
isApple ? (
<AppleLogo className="h-5 w-5 shrink-0 text-muted-foreground" />
) : (
<GpuIcon className="h-5 w-5 shrink-0 text-accent" />
)
) : (
<Cpu className="h-5 w-5 shrink-0 text-muted-foreground" />
)}
<div className="flex-1 min-w-0 space-y-0.5">
<div className="text-sm font-medium">{hasGpu ? gpuName : 'CPU Only'}</div>
<div className="flex flex-wrap items-center gap-x-3 gap-y-1 text-xs text-muted-foreground">
{hasGpu ? (
<>
<span>{gpuBackend}</span>
{showBackendVariant && (
<>
<span className="text-border">|</span>
<span className="uppercase">{health.backend_variant}</span>
</>
)}
{health.vram_used_mb != null && health.vram_used_mb > 0 && (
<>
<span className="text-border">|</span>
<span>{health.vram_used_mb.toFixed(0)} MB VRAM</span>
</>
)}
</>
) : (
<span>No GPU acceleration detected</span>
)}
</div>
</div>
{hasGpu && (
<div className="flex items-center gap-2 rounded-full border border-accent/30 px-2.5 py-0.5">
<span className="relative flex h-1.5 w-1.5">
<span className="absolute inline-flex h-full w-full animate-ping rounded-full bg-accent/60" />
<span className="relative inline-flex h-1.5 w-1.5 rounded-full bg-accent shadow-[0_0_4px_1px_hsl(var(--accent)/0.4)]" />
</span>
<span className="text-[10px] font-medium text-muted-foreground">Active</span>
</div>
)}
</div>
</div>
);
}
export function GpuPage() {
const platform = usePlatform();
const queryClient = useQueryClient();
const serverUrl = useServerStore((state) => state.serverUrl);
const { data: health } = useServerHealth();
const [restartPhase, setRestartPhase] = useState<RestartPhase>('idle');
const [error, setError] = useState<string | null>(null);
const [downloadProgress, setDownloadProgress] = useState<CudaDownloadProgress | null>(null);
const healthPollRef = useRef<ReturnType<typeof setInterval> | null>(null);
const {
data: cudaStatus,
isLoading: _cudaStatusLoading,
refetch: refetchCudaStatus,
} = useQuery({
queryKey: ['cuda-status', serverUrl],
queryFn: () => apiClient.getCudaStatus(),
refetchInterval: (query) => (query.state.status === 'pending' ? false : 10000),
retry: 1,
enabled: !!health,
});
const isCurrentlyCuda = health?.backend_variant === 'cuda';
const cudaAvailable = cudaStatus?.available ?? false;
const cudaDownloading = cudaStatus?.downloading ?? false;
useEffect(() => {
return () => {
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
};
}, []);
useEffect(() => {
if (!cudaDownloading || !serverUrl) return;
const eventSource = new EventSource(`${serverUrl}/backend/cuda-progress`);
eventSource.onmessage = (event) => {
try {
const data = JSON.parse(event.data) as CudaDownloadProgress;
setDownloadProgress(data);
if (data.status === 'complete') {
eventSource.close();
setDownloadProgress(null);
refetchCudaStatus();
} else if (data.status === 'error') {
eventSource.close();
setError(data.error || 'Download failed');
setDownloadProgress(null);
refetchCudaStatus();
}
} catch (e) {
console.error('Error parsing CUDA progress event:', e);
}
};
eventSource.onerror = () => {
eventSource.close();
};
return () => {
eventSource.close();
};
}, [cudaDownloading, serverUrl, refetchCudaStatus]);
const clearHealthPolling = useCallback(() => {
if (healthPollRef.current) {
clearInterval(healthPollRef.current);
healthPollRef.current = null;
}
}, []);
const startHealthPolling = useCallback(() => {
clearHealthPolling();
healthPollRef.current = setInterval(async () => {
try {
const result = await apiClient.getHealth();
if (result.status === 'healthy') {
clearHealthPolling();
setRestartPhase('ready');
queryClient.invalidateQueries();
setTimeout(() => setRestartPhase('idle'), 2000);
}
} catch {
// Server still down, keep polling
}
}, 1000);
}, [queryClient, clearHealthPolling]);
const restartServerWithPolling = useCallback(
async (errorMessage: string) => {
setRestartPhase('stopping');
try {
await platform.lifecycle.restartServer();
setRestartPhase('waiting');
startHealthPolling();
} catch (e: unknown) {
clearHealthPolling();
setRestartPhase('idle');
throw new Error(e instanceof Error ? e.message : errorMessage);
}
},
[platform, startHealthPolling, clearHealthPolling],
);
const handleDownload = async () => {
setError(null);
try {
await apiClient.downloadCudaBackend();
refetchCudaStatus();
} catch (e: unknown) {
const msg = e instanceof Error ? e.message : 'Failed to start download';
if (msg.includes('already downloaded')) {
refetchCudaStatus();
} else {
setError(msg);
}
}
};
const handleRestart = async () => {
setError(null);
try {
await restartServerWithPolling('Restart failed');
} catch (e: unknown) {
setError(e instanceof Error ? e.message : 'Restart failed');
}
};
const handleSwitchToCpu = async () => {
setError(null);
setRestartPhase('stopping');
try {
await apiClient.deleteCudaBackend();
await restartServerWithPolling('Failed to switch to CPU');
} catch (e: unknown) {
setError(e instanceof Error ? e.message : 'Failed to switch to CPU');
refetchCudaStatus();
}
};
const handleDelete = async () => {
setError(null);
try {
await apiClient.deleteCudaBackend();
refetchCudaStatus();
} catch (e: unknown) {
setError(e instanceof Error ? e.message : 'Failed to delete CUDA backend');
}
};
const formatBytes = (bytes: number): string => {
if (bytes === 0) return '0 B';
const k = 1024;
const sizes = ['B', 'KB', 'MB', 'GB'];
const i = Math.floor(Math.log(bytes) / Math.log(k));
return `${(bytes / k ** i).toFixed(1)} ${sizes[i]}`;
};
if (!health) return null;
const hasNativeGpu =
health.gpu_available &&
!isCurrentlyCuda &&
health.gpu_type &&
!health.gpu_type.includes('CUDA');
return (
<div className="space-y-8 max-w-2xl">
<GpuInfoCard health={health} />
{/* CUDA section — only when no native GPU and not already on CUDA */}
{!hasNativeGpu && !isCurrentlyCuda && (
<SettingSection
title="CUDA Backend"
description="NVIDIA GPU acceleration via a downloadable CUDA backend."
>
{/* Download progress */}
{cudaDownloading && downloadProgress && (
<SettingRow title="Downloading CUDA backend...">
<div className="space-y-1.5">
<Progress value={downloadProgress.progress} className="h-2" />
<div className="flex items-center justify-between text-xs text-muted-foreground">
<span>
{downloadProgress.filename ||
(cudaAvailable ? 'Updating...' : 'Downloading...')}
</span>
<span>
{downloadProgress.total > 0
? `${formatBytes(downloadProgress.current)} / ${formatBytes(downloadProgress.total)}`
: `${downloadProgress.progress.toFixed(1)}%`}
</span>
</div>
</div>
</SettingRow>
)}
{/* Restart in progress */}
{restartPhase !== 'idle' && (
<SettingRow
title={
restartPhase === 'ready'
? 'Server restarted successfully'
: restartPhase === 'waiting'
? 'Restarting server...'
: 'Stopping server...'
}
action={<Loader2 className="h-4 w-4 animate-spin text-muted-foreground" />}
/>
)}
{/* Error */}
{error && (
<SettingRow title="Error">
<div className="flex items-center gap-2 text-sm text-destructive">
<AlertCircle className="h-4 w-4 shrink-0" />
<span>{error}</span>
</div>
</SettingRow>
)}
{/* Actions */}
{restartPhase === 'idle' && !cudaDownloading && (
<>
{!cudaAvailable && !isCurrentlyCuda && (
<SettingRow
title="Download CUDA backend"
description="~2.4 GB download. Requires an NVIDIA GPU with CUDA support."
action={
<Button onClick={handleDownload} size="sm">
<Download className="h-3.5 w-3.5 mr-1.5" />
Download
</Button>
}
/>
)}
{cudaAvailable && !isCurrentlyCuda && platform.metadata.isTauri && (
<SettingRow
title="Switch to CUDA backend"
description="CUDA backend is downloaded and ready. Restart to enable."
action={
<Button onClick={handleRestart} size="sm">
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
Restart
</Button>
}
/>
)}
{isCurrentlyCuda && platform.metadata.isTauri && (
<SettingRow
title="Switch to CPU backend"
description="Disable GPU acceleration. You can re-download CUDA later."
action={
<Button onClick={handleSwitchToCpu} variant="outline" size="sm">
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
Switch
</Button>
}
/>
)}
{cudaAvailable && !isCurrentlyCuda && (
<SettingRow
title="Remove CUDA backend"
description="Delete the downloaded CUDA binary to free disk space."
action={
<Button
onClick={handleDelete}
variant="ghost"
size="sm"
className="text-muted-foreground hover:text-destructive"
>
<Trash2 className="h-3.5 w-3.5 mr-1.5" />
Remove
</Button>
}
/>
)}
</>
)}
</SettingSection>
)}
<p className="text-xs text-muted-foreground/60 leading-relaxed">
Voicebox automatically detects and uses the best available GPU on your system. On Apple
Silicon Macs, the MLX backend runs natively on the Neural Engine and GPU via Metal
Performance Shaders (MPS), with no additional setup required. On Windows and Linux with
NVIDIA GPUs, you can download an optional CUDA backend for hardware-accelerated inference.
AMD ROCm, Intel XPU, and DirectML are also supported where available through PyTorch. When
no GPU is detected, Voicebox falls back to CPU — all engines still work, just slower.
</p>
</div>
);
}
+104
View File
@@ -0,0 +1,104 @@
import { useEffect, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import { cn } from '@/lib/utils/cn';
import { type LogEntry, useLogStore } from '@/stores/logStore';
function formatTime(timestamp: number): string {
const d = new Date(timestamp);
return d.toLocaleTimeString(undefined, {
hour: '2-digit',
minute: '2-digit',
second: '2-digit',
hour12: false,
});
}
function LogLine({ entry }: { entry: LogEntry }) {
return (
<div className="flex gap-3 font-mono text-xs leading-5 hover:bg-muted/30">
<span className="text-muted-foreground/50 select-none shrink-0">
{formatTime(entry.timestamp)}
</span>
<span
className={cn(
'whitespace-pre-wrap break-all',
entry.stream === 'stderr' ? 'text-orange-400/80' : 'text-muted-foreground',
)}
>
{entry.line}
</span>
</div>
);
}
export function LogsPage() {
const entries = useLogStore((s) => s.entries);
const clear = useLogStore((s) => s.clear);
const containerRef = useRef<HTMLDivElement>(null);
const [autoScroll, setAutoScroll] = useState(true);
// Auto-scroll to bottom when new entries arrive
useEffect(() => {
if (autoScroll && containerRef.current) {
containerRef.current.scrollTop = containerRef.current.scrollHeight;
}
}, [entries.length, autoScroll]);
// Detect manual scroll to disable auto-scroll
const handleScroll = () => {
const el = containerRef.current;
if (!el) return;
const atBottom = el.scrollHeight - el.scrollTop - el.clientHeight < 40;
setAutoScroll(atBottom);
};
return (
<div className="flex flex-col h-full min-h-0">
<div className="flex items-center justify-between mb-3">
<div>
<h3 className="text-sm font-medium">Server Logs</h3>
<p className="text-sm text-muted-foreground">
{entries.length} {entries.length === 1 ? 'line' : 'lines'}
</p>
</div>
<div className="flex items-center gap-2">
{!autoScroll && (
<Button
variant="outline"
size="sm"
onClick={() => {
setAutoScroll(true);
containerRef.current?.scrollTo({ top: containerRef.current.scrollHeight });
}}
>
Scroll to bottom
</Button>
)}
<Button variant="outline" size="sm" onClick={clear}>
Clear
</Button>
</div>
</div>
<div
ref={containerRef}
onScroll={handleScroll}
className="flex-1 min-h-0 overflow-y-auto rounded-md border bg-black/20 p-3"
>
{entries.length === 0 ? (
<div className="text-sm text-muted-foreground/50 font-mono space-y-1">
<p>No log output yet.</p>
{!import.meta.env?.PROD && (
<p>
Server logs are only captured when the app manages the server process (production
builds).
</p>
)}
</div>
) : (
entries.map((entry) => <LogLine key={entry.id} entry={entry} />)
)}
</div>
</div>
);
}
+63 -20
View File
@@ -1,27 +1,70 @@
import { ConnectionForm } from '@/components/ServerSettings/ConnectionForm';
import { ServerStatus } from '@/components/ServerSettings/ServerStatus';
import { UpdateStatus } from '@/components/ServerSettings/UpdateStatus';
import { Link, Outlet, useMatchRoute } from '@tanstack/react-router';
import { BOTTOM_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import { cn } from '@/lib/utils/cn';
import { usePlatform } from '@/platform/PlatformContext';
import { usePlayerStore } from '@/stores/playerStore';
export function ServerTab() {
interface SettingsTab {
label: string;
path:
| '/settings'
| '/settings/generation'
| '/settings/gpu'
| '/settings/logs'
| '/settings/changelog'
| '/settings/about';
tauriOnly?: boolean;
}
const tabs: SettingsTab[] = [
{ label: 'General', path: '/settings' },
{ label: 'Generation', path: '/settings/generation' },
{ label: 'GPU', path: '/settings/gpu', tauriOnly: true },
{ label: 'Logs', path: '/settings/logs', tauriOnly: true },
{ label: 'Changelog', path: '/settings/changelog' },
{ label: 'About', path: '/settings/about' },
];
export function SettingsLayout() {
const platform = usePlatform();
const isPlayerVisible = !!usePlayerStore((state) => state.audioUrl);
const matchRoute = useMatchRoute();
return (
<div className="space-y-4 overflow-y-auto flex flex-col">
<div className="grid gap-4 md:grid-cols-2">
<ConnectionForm />
<ServerStatus />
</div>
{platform.metadata.isTauri && <UpdateStatus />}
<div className="py-8 text-center text-sm text-muted-foreground">
Created by{' '}
<a
href="https://github.com/jamiepine"
target="_blank"
rel="noopener noreferrer"
className="text-accent hover:underline"
>
Jamie Pine
</a>
<div className="flex flex-col h-full min-h-0">
<nav className="flex gap-1 border-b shrink-0">
{tabs.map((tab) => {
if (tab.tauriOnly && !platform.metadata.isTauri) return null;
const isActive =
tab.path === '/settings'
? matchRoute({ to: tab.path, fuzzy: false })
: matchRoute({ to: tab.path });
return (
<Link
key={tab.path}
to={tab.path}
className={cn(
'px-4 py-2 text-sm font-medium transition-colors border-b-2 -mb-px',
isActive
? 'border-accent text-foreground'
: 'border-transparent text-muted-foreground hover:text-foreground hover:border-muted-foreground/30',
)}
>
{tab.label}
</Link>
);
})}
</nav>
<div
className={cn(
'flex-1 overflow-y-auto pt-6 pb-6 px-2 -mx-2',
isPlayerVisible && BOTTOM_SAFE_AREA_PADDING,
)}
>
<Outlet />
</div>
</div>
);
@@ -0,0 +1,62 @@
import type { ReactNode } from 'react';
/**
* A section header with title and optional description, separated by a border.
*/
export function SettingSection({
title,
description,
children,
}: {
title?: string;
description?: string;
children: ReactNode;
}) {
return (
<div className="space-y-1">
{title && <h3 className="text-sm font-medium">{title}</h3>}
{description && <p className="text-sm text-muted-foreground">{description}</p>}
<div className={`${title || description ? 'pt-3' : ''} space-y-0 divide-y divide-border/60`}>
{children}
</div>
</div>
);
}
/**
* A single settings row: label+description on the left, action on the right.
* Use for toggles, inputs, buttons, badges — any control type.
*/
export function SettingRow({
title,
description,
htmlFor,
action,
children,
}: {
title: string;
description?: string;
htmlFor?: string;
/** Right-aligned control (checkbox, button, badge, etc.) */
action?: ReactNode;
/** Full-width content rendered below the label row (for sliders, inputs, etc.) */
children?: ReactNode;
}) {
return (
<div className="py-3">
<div className="flex items-center justify-between gap-8">
<div className="min-w-0">
<label
htmlFor={htmlFor}
className={`text-sm font-medium leading-none select-none ${htmlFor ? 'cursor-pointer' : ''}`}
>
{title}
</label>
{description && <p className="text-sm text-muted-foreground mt-0.5">{description}</p>}
</div>
{action && <div className="shrink-0">{action}</div>}
</div>
{children && <div className="mt-3">{children}</div>}
</div>
);
}
+58 -30
View File
@@ -1,9 +1,12 @@
import { Link, useMatchRoute } from '@tanstack/react-router';
import { Box, BookOpen, Loader2, Mic, Server, Speaker, Volume2 } from 'lucide-react';
import { AudioLines, Box, Mic, Settings, Speaker, Volume2, Wand2 } from 'lucide-react';
import { useEffect, useState } from 'react';
import voiceboxLogo from '@/assets/voicebox-logo.png';
import { cn } from '@/lib/utils/cn';
import { useGenerationStore } from '@/stores/generationStore';
import { usePlatform } from '@/platform/PlatformContext';
import type { UpdateStatus } from '@/platform/types';
import { usePlayerStore } from '@/stores/playerStore';
import { version } from '../../package.json';
interface SidebarProps {
isMacOS?: boolean;
@@ -11,18 +14,21 @@ interface SidebarProps {
const tabs = [
{ id: 'main', path: '/', icon: Volume2, label: 'Generate' },
{ id: 'stories', path: '/stories', icon: BookOpen, label: 'Stories' },
{ id: 'stories', path: '/stories', icon: AudioLines, label: 'Stories' },
{ id: 'voices', path: '/voices', icon: Mic, label: 'Voices' },
{ id: 'effects', path: '/effects', icon: Wand2, label: 'Effects' },
{ id: 'audio', path: '/audio', icon: Speaker, label: 'Audio' },
{ id: 'models', path: '/models', icon: Box, label: 'Models' },
{ id: 'server', path: '/server', icon: Server, label: 'Server' },
{ id: 'settings', path: '/settings', icon: Settings, label: 'Settings' },
];
export function Sidebar({ isMacOS }: SidebarProps) {
const isGenerating = useGenerationStore((state) => state.isGenerating);
const audioUrl = usePlayerStore((state) => state.audioUrl);
const isPlayerVisible = !!audioUrl;
const matchRoute = useMatchRoute();
const isPlayerOpen = !!usePlayerStore((s) => s.audioUrl);
const platform = usePlatform();
const [updateStatus, setUpdateStatus] = useState<UpdateStatus>(platform.updater.getStatus());
useEffect(() => platform.updater.subscribe(setUpdateStatus), [platform.updater]);
return (
<div
@@ -33,51 +39,73 @@ export function Sidebar({ isMacOS }: SidebarProps) {
>
{/* Logo */}
<div className="mb-2">
<img src={voiceboxLogo} alt="Voicebox" className="w-12 h-12 object-contain" />
<img
src={voiceboxLogo}
alt="Voicebox"
className="w-12 h-12 object-contain"
style={{
filter:
'drop-shadow(0 0 6px hsl(var(--accent) / 0.5)) drop-shadow(0 0 14px hsl(var(--accent) / 0.35)) drop-shadow(0 0 28px hsl(var(--accent) / 0.2))',
}}
/>
</div>
{/* Navigation Buttons */}
<div className="flex flex-col gap-3">
{tabs.map((tab) => {
{tabs.map((tab, index) => {
const Icon = tab.icon;
// For index route, use exact match; for others, use default matching
const isActive =
tab.path === '/'
? matchRoute({ to: '/', exact: true })
: matchRoute({ to: tab.path });
? matchRoute({ to: '/', fuzzy: false })
: matchRoute({ to: tab.path, fuzzy: true });
// Accent fades as buttons get further from the logo
const accentOpacity = Math.max(0.08, 0.5 - index * 0.07);
return (
<Link
key={tab.id}
to={tab.path}
className={cn(
'w-12 h-12 rounded-full flex items-center justify-center transition-all duration-200',
'hover:bg-muted/50',
isActive ? 'bg-muted/50 text-foreground shadow-lg' : 'text-muted-foreground',
'relative w-12 h-12 rounded-full flex items-center justify-center transition-all duration-200 overflow-hidden',
isActive
? 'bg-white/[0.07] text-foreground shadow-lg backdrop-blur-sm border border-white/[0.08]'
: 'text-muted-foreground hover:bg-muted/50',
)}
title={tab.label}
aria-label={tab.label}
>
<Icon className="h-5 w-5" />
{isActive && (
<div
className="absolute inset-0 rounded-full pointer-events-none"
style={{
maskImage: 'linear-gradient(to bottom, black, transparent 60%)',
WebkitMaskImage: 'linear-gradient(to bottom, black, transparent 60%)',
border: `1px solid hsl(var(--accent) / ${accentOpacity})`,
}}
/>
)}
<Icon className="h-5 w-5 relative z-10" />
</Link>
);
})}
</div>
{/* Spacer to push loader to bottom */}
<div className="flex-1" />
{/* Generation Loader */}
{isGenerating && (
<div
className={cn(
'w-full flex items-center justify-center transition-all duration-200',
isPlayerVisible ? 'mb-[120px]' : 'mb-0',
)}
>
<Loader2 className="h-6 w-6 text-accent animate-spin" />
</div>
)}
{/* Version */}
<div
className="mt-auto flex flex-col items-center gap-1.5 transition-all duration-300"
style={{ paddingBottom: isPlayerOpen ? '7rem' : undefined }}
>
<span className="text-[10px] text-muted-foreground/50">v{version}</span>
{updateStatus.available && (
<Link
to="/settings"
className="text-[9px] font-semibold tracking-wide uppercase px-2 py-0.5 rounded-full bg-accent/15 text-accent hover:bg-accent/25 transition-colors"
>
Update
</Link>
)}
</div>
</div>
);
}
+4 -1
View File
@@ -1,8 +1,11 @@
import { FloatingGenerateBox } from '@/components/Generation/FloatingGenerateBox';
import { usePlayerStore } from '@/stores/playerStore';
import { StoryContent } from './StoryContent';
import { StoryList } from './StoryList';
export function StoriesTab() {
const audioUrl = usePlayerStore((state) => state.audioUrl);
return (
<div className="flex flex-col h-full min-h-0 overflow-hidden">
{/* Main content area */}
@@ -18,7 +21,7 @@ export function StoriesTab() {
</div>
{/* Floating Generate Box - position is managed via storyStore.trackEditorHeight */}
<FloatingGenerateBox showVoiceSelector />
<FloatingGenerateBox showVoiceSelector isPlayerOpen={!!audioUrl} />
</div>
</div>
);
+12 -16
View File
@@ -87,7 +87,7 @@ export function StoryChatItem({
alt={`${item.profile_name} avatar`}
className={cn(
'h-full w-full object-cover transition-all duration-200',
!isCurrentlyPlaying && 'grayscale'
!isCurrentlyPlaying && 'grayscale',
)}
onError={() => setAvatarError(true)}
/>
@@ -127,7 +127,10 @@ export function StoryChatItem({
<Play className="mr-2 h-4 w-4" />
Play from here
</DropdownMenuItem>
<DropdownMenuItem onClick={onRemove} className="text-destructive focus:text-destructive">
<DropdownMenuItem
onClick={onRemove}
className="text-destructive focus:text-destructive"
>
<Trash2 className="mr-2 h-4 w-4" />
Remove from Story
</DropdownMenuItem>
@@ -139,15 +142,12 @@ export function StoryChatItem({
}
// Sortable wrapper component
export function SortableStoryChatItem(props: Omit<StoryChatItemProps, 'dragHandleProps' | 'isDragging'>) {
const {
attributes,
listeners,
setNodeRef,
transform,
transition,
isDragging,
} = useSortable({ id: props.item.generation_id });
export function SortableStoryChatItem(
props: Omit<StoryChatItemProps, 'dragHandleProps' | 'isDragging'>,
) {
const { attributes, listeners, setNodeRef, transform, transition, isDragging } = useSortable({
id: props.item.generation_id,
});
const style = {
transform: CSS.Transform.toString(transform),
@@ -156,11 +156,7 @@ export function SortableStoryChatItem(props: Omit<StoryChatItemProps, 'dragHandl
return (
<div ref={setNodeRef} style={style} {...attributes}>
<StoryChatItem
{...props}
dragHandleProps={listeners}
isDragging={isDragging}
/>
<StoryChatItem {...props} dragHandleProps={listeners} isDragging={isDragging} />
</div>
);
}
+33 -6
View File
@@ -13,8 +13,11 @@ import {
sortableKeyboardCoordinates,
verticalListSortingStrategy,
} from '@dnd-kit/sortable';
import { Link } from '@tanstack/react-router';
import { AnimatePresence, motion } from 'framer-motion';
import { Download, Plus } from 'lucide-react';
import { useEffect, useMemo, useRef, useState } from 'react';
import Loader from 'react-loaders';
import { Button } from '@/components/ui/button';
import { Input } from '@/components/ui/input';
import { Popover, PopoverContent, PopoverTrigger } from '@/components/ui/popover';
@@ -28,6 +31,7 @@ import {
useStory,
} from '@/lib/hooks/useStories';
import { useStoryPlayback } from '@/lib/hooks/useStoryPlayback';
import { useGenerationStore } from '@/stores/generationStore';
import { useStoryStore } from '@/stores/storyStore';
import { SortableStoryChatItem } from './StoryChatItem';
@@ -40,6 +44,7 @@ export function StoryContent() {
const addStoryItem = useAddStoryItem();
const { toast } = useToast();
const scrollRef = useRef<HTMLDivElement>(null);
const pendingCount = useGenerationStore((s) => s.pendingGenerationIds.size);
// Add generation popover state
const [searchQuery, setSearchQuery] = useState('');
@@ -53,9 +58,9 @@ export function StoryContent() {
const query = searchQuery.toLowerCase();
return historyData.items.filter(
(gen) =>
gen.status === 'completed' &&
!storyGenerationIds.has(gen.id) &&
(gen.text.toLowerCase().includes(query) ||
gen.profile_name.toLowerCase().includes(query)),
(gen.text.toLowerCase().includes(query) || gen.profile_name.toLowerCase().includes(query)),
);
}, [historyData, story, searchQuery]);
@@ -267,7 +272,31 @@ export function StoryContent() {
<p className="text-sm text-muted-foreground mt-1">{story.description}</p>
)}
</div>
<div className="flex gap-2">
<div className="flex gap-2 items-center">
<AnimatePresence>
{pendingCount > 0 && (
<motion.div
initial={{ opacity: 0, scale: 0.9, width: 0 }}
animate={{ opacity: 1, scale: 1, width: 'auto' }}
exit={{ opacity: 0, scale: 0.9, width: 0 }}
transition={{ duration: 0.2 }}
>
<Link
to="/"
className="flex items-center gap-2 h-8 pl-1.5 pr-3 rounded-full bg-card border border-border hover:bg-muted/50 transition-all duration-200 cursor-pointer"
>
<div className="shrink-0 w-10 h-5 overflow-hidden flex items-center justify-center">
<div className="scale-[0.45]">
<Loader type="line-scale" active />
</div>
</div>
<span className="text-xs text-muted-foreground whitespace-nowrap">
Generating {pendingCount} {pendingCount === 1 ? 'audio' : 'audios'}
</span>
</Link>
</motion.div>
)}
</AnimatePresence>
<Popover open={isAddOpen} onOpenChange={setIsAddOpen}>
<PopoverTrigger asChild>
<Button variant="outline" size="sm">
@@ -287,9 +316,7 @@ export function StoryContent() {
<div className="max-h-60 overflow-y-auto">
{availableGenerations.length === 0 ? (
<div className="p-4 text-center text-sm text-muted-foreground">
{searchQuery
? 'No matching generations found'
: 'No available generations'}
{searchQuery ? 'No matching generations found' : 'No available generations'}
</div>
) : (
availableGenerations.map((gen) => (
+97 -67
View File
@@ -1,5 +1,5 @@
import { Plus, BookOpen, MoreHorizontal, Pencil, Trash2 } from 'lucide-react';
import { useState } from 'react';
import { BookOpen, MoreHorizontal, Pencil, Plus, Trash2 } from 'lucide-react';
import { useEffect, useState } from 'react';
import {
AlertDialog,
AlertDialogAction,
@@ -29,7 +29,13 @@ import { Input } from '@/components/ui/input';
import { Label } from '@/components/ui/label';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
import { useStories, useCreateStory, useUpdateStory, useDeleteStory } from '@/lib/hooks/useStories';
import {
useCreateStory,
useDeleteStory,
useStories,
useStory,
useUpdateStory,
} from '@/lib/hooks/useStories';
import { cn } from '@/lib/utils/cn';
import { formatDate } from '@/lib/utils/format';
import { useStoryStore } from '@/stores/storyStore';
@@ -38,6 +44,8 @@ export function StoryList() {
const { data: stories, isLoading } = useStories();
const selectedStoryId = useStoryStore((state) => state.selectedStoryId);
const setSelectedStoryId = useStoryStore((state) => state.setSelectedStoryId);
const trackEditorHeight = useStoryStore((state) => state.trackEditorHeight);
const { data: selectedStory } = useStory(selectedStoryId);
const createStory = useCreateStory();
const updateStory = useUpdateStory();
const deleteStory = useDeleteStory();
@@ -54,6 +62,13 @@ export function StoryList() {
const [newStoryDescription, setNewStoryDescription] = useState('');
const { toast } = useToast();
// Auto-select the first story when the list loads with no selection
useEffect(() => {
if (!selectedStoryId && stories && stories.length > 0) {
setSelectedStoryId(stories[0].id);
}
}, [selectedStoryId, stories, setSelectedStoryId]);
const handleCreateStory = () => {
if (!newStoryName.trim()) {
toast({
@@ -170,20 +185,29 @@ export function StoryList() {
}
const storyList = stories || [];
const hasTrackEditor = selectedStoryId && selectedStory && selectedStory.items.length > 0;
return (
<div className="flex flex-col h-full min-h-0">
{/* Header */}
<div className="flex items-center justify-between mb-4 px-1">
<h2 className="text-2xl font-bold">Stories</h2>
<Button onClick={() => setCreateDialogOpen(true)} size="sm">
<Plus className="mr-2 h-4 w-4" />
New Story
</Button>
<div className="h-full flex flex-col relative overflow-hidden">
{/* Scroll Mask */}
<div className="absolute top-0 left-0 right-0 h-16 bg-gradient-to-b from-background to-transparent z-10 pointer-events-none" />
{/* Fixed Header */}
<div className="absolute top-0 left-0 right-0 z-20">
<div className="flex items-center justify-between mb-4 px-1">
<h2 className="text-2xl font-bold">Stories</h2>
<Button onClick={() => setCreateDialogOpen(true)} size="sm">
<Plus className="mr-2 h-4 w-4" />
New Story
</Button>
</div>
</div>
{/* Story List */}
<div className="flex-1 min-h-0 overflow-y-auto space-y-2">
{/* Scrollable Story List */}
<div
className="flex-1 overflow-y-auto pt-14 relative z-0"
style={{ paddingBottom: hasTrackEditor ? `${trackEditorHeight + 140}px` : '170px' }}
>
{storyList.length === 0 ? (
<div className="text-center py-12 px-5 border-2 border-dashed border-muted rounded-2xl text-muted-foreground">
<BookOpen className="h-12 w-12 mx-auto mb-4 opacity-50" />
@@ -191,62 +215,68 @@ export function StoryList() {
<p className="text-xs mt-2">Create your first story to get started</p>
</div>
) : (
storyList.map((story) => (
<div
key={story.id}
className={cn(
'h-24 p-4 border rounded-2xl transition-colors group flex items-center',
selectedStoryId === story.id && 'bg-muted border-primary',
)}
>
<div className="flex items-start justify-between gap-2 w-full min-w-0">
<button
type="button"
className="flex-1 min-w-0 text-left cursor-pointer overflow-hidden"
onClick={() => setSelectedStoryId(story.id)}
>
<h3 className="font-medium truncate">{story.name}</h3>
{story.description && (
<p className="text-sm text-muted-foreground mt-1 truncate">
{story.description}
</p>
)}
<div className="flex items-center gap-3 mt-2 text-xs text-muted-foreground">
<span>
{story.item_count} {story.item_count === 1 ? 'item' : 'items'}
</span>
<span>•</span>
<span>{formatDate(story.updated_at)}</span>
<div className="space-y-0.5">
{storyList.map((story) => (
<div
key={story.id}
role="button"
tabIndex={0}
className={cn(
'px-5 py-3 rounded-lg transition-colors group flex items-center cursor-pointer',
selectedStoryId === story.id ? 'bg-muted' : 'hover:bg-muted/50',
)}
aria-label={`Story ${story.name}, ${story.item_count} ${story.item_count === 1 ? 'item' : 'items'}, ${formatDate(story.updated_at)}`}
aria-pressed={selectedStoryId === story.id}
onClick={() => setSelectedStoryId(story.id)}
onKeyDown={(e) => {
if (e.target !== e.currentTarget) return;
if (e.key === 'Enter' || e.key === ' ') {
e.preventDefault();
setSelectedStoryId(story.id);
}
}}
>
<div className="flex items-start justify-between gap-2 w-full min-w-0">
<div className="flex-1 min-w-0 text-left overflow-hidden">
<h3 className="text-sm font-medium truncate">{story.name}</h3>
<div className="flex items-center gap-2 mt-1 text-xs text-muted-foreground">
<span>
{story.item_count} {story.item_count === 1 ? 'item' : 'items'}
</span>
<span>·</span>
<span>{formatDate(story.updated_at)}</span>
</div>
</div>
</button>
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button
variant="ghost"
size="icon"
className="h-8 w-8 opacity-0 group-hover:opacity-100 transition-opacity"
onClick={(e) => e.stopPropagation()}
>
<MoreHorizontal className="h-4 w-4" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="end">
<DropdownMenuItem onClick={() => handleEditClick(story)}>
<Pencil className="mr-2 h-4 w-4" />
Edit
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleDeleteClick(story.id)}
className="text-destructive focus:text-destructive"
>
<Trash2 className="mr-2 h-4 w-4" />
Delete
</DropdownMenuItem>
</DropdownMenuContent>
</DropdownMenu>
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button
variant="ghost"
size="icon"
className="h-7 w-7 opacity-0 group-hover:opacity-100 transition-opacity"
onClick={(e) => e.stopPropagation()}
aria-label={`Actions for ${story.name}`}
>
<MoreHorizontal className="h-3.5 w-3.5" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="end">
<DropdownMenuItem onClick={() => handleEditClick(story)}>
<Pencil className="mr-2 h-4 w-4" />
Edit
</DropdownMenuItem>
<DropdownMenuItem
onClick={() => handleDeleteClick(story.id)}
className="text-destructive focus:text-destructive"
>
<Trash2 className="mr-2 h-4 w-4" />
Delete
</DropdownMenuItem>
</DropdownMenuContent>
</DropdownMenu>
</div>
</div>
</div>
))
))}
</div>
)}
</div>
@@ -1,5 +1,7 @@
import {
Check,
Copy,
GalleryVerticalEnd,
GripHorizontal,
Minus,
Pause,
@@ -12,6 +14,12 @@ import {
import { useCallback, useEffect, useMemo, useRef, useState } from 'react';
import WaveSurfer from 'wavesurfer.js';
import { Button } from '@/components/ui/button';
import {
DropdownMenu,
DropdownMenuContent,
DropdownMenuItem,
DropdownMenuTrigger,
} from '@/components/ui/dropdown-menu';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import type { StoryItemDetail } from '@/lib/api/types';
@@ -19,6 +27,7 @@ import {
useDuplicateStoryItem,
useMoveStoryItem,
useRemoveStoryItem,
useSetStoryItemVersion,
useSplitStoryItem,
useTrimStoryItem,
} from '@/lib/hooks/useStories';
@@ -28,12 +37,14 @@ import { useStoryStore } from '@/stores/storyStore';
// Clip waveform component with trim support
function ClipWaveform({
generationId,
versionId,
width,
trimStartMs,
trimEndMs,
duration,
}: {
generationId: string;
versionId?: string;
width: number;
trimStartMs: number;
trimEndMs: number;
@@ -79,7 +90,9 @@ function ClipWaveform({
wavesurferRef.current = wavesurfer;
const audioUrl = apiClient.getAudioUrl(generationId);
const audioUrl = versionId
? apiClient.getVersionAudioUrl(versionId)
: apiClient.getAudioUrl(generationId);
wavesurfer.load(audioUrl).catch(() => {
// Ignore load errors
});
@@ -88,7 +101,7 @@ function ClipWaveform({
wavesurfer.destroy();
wavesurferRef.current = null;
};
}, [generationId, fullWaveformWidth]);
}, [generationId, versionId, fullWaveformWidth]);
return (
<div className="w-full h-full opacity-60 overflow-hidden">
@@ -135,12 +148,57 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
const splitItem = useSplitStoryItem();
const duplicateItem = useDuplicateStoryItem();
const removeItem = useRemoveStoryItem();
const setItemVersion = useSetStoryItemVersion();
const { toast } = useToast();
// Selection state
const selectedClipId = useStoryStore((state) => state.selectedClipId);
const setSelectedClipId = useStoryStore((state) => state.setSelectedClipId);
// Selected clip item (for version picker)
const selectedItem = useMemo(
() => (selectedClipId ? items.find((i) => i.id === selectedClipId) : undefined),
[selectedClipId, items],
);
const selectedItemVersions = selectedItem?.versions;
const hasMultipleVersions = selectedItemVersions && selectedItemVersions.length > 1;
// Determine which version label is active for the selected clip
const activeVersionLabel = useMemo(() => {
if (!selectedItem || !selectedItemVersions) return null;
// If the item has a pinned version_id, find its label
if (selectedItem.version_id) {
const pinned = selectedItemVersions.find((v) => v.id === selectedItem.version_id);
return pinned?.label ?? null;
}
// Otherwise use the generation's default version
const defaultVersion = selectedItemVersions.find((v) => v.is_default);
return defaultVersion?.label ?? null;
}, [selectedItem, selectedItemVersions]);
const handleSetVersion = useCallback(
(versionId: string | null) => {
if (!selectedClipId) return;
setItemVersion.mutate(
{
storyId,
itemId: selectedClipId,
data: { version_id: versionId },
},
{
onError: (error) => {
toast({
title: 'Failed to set version',
description: error instanceof Error ? error.message : String(error),
variant: 'destructive',
});
},
},
);
},
[selectedClipId, storyId, setItemVersion, toast],
);
// Trim state
const [trimmingItem, setTrimmingItem] = useState<string | null>(null);
const [trimSide, setTrimSide] = useState<'start' | 'end' | null>(null);
@@ -313,7 +371,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
}
}, [isResizing, handleResizeMove, handleResizeEnd]);
const handleTimelineClick = (e: React.MouseEvent<HTMLDivElement>) => {
const handleTimelineClick = (e: React.MouseEvent<HTMLElement>) => {
if (!tracksRef.current || draggingItem || trimmingItem) return;
const rect = tracksRef.current.getBoundingClientRect();
const x = e.clientX - rect.left + tracksRef.current.scrollLeft;
@@ -442,7 +500,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
}, [trimmingItem, trimSide, tempTrimValues, storyId, trimItem, toast]);
const handleSplit = useCallback(() => {
if (!selectedClipId) return;
if (!selectedClipId || splitItem.isPending) return;
const item = items.find((i) => i.id === selectedClipId);
if (!item) return;
@@ -736,6 +794,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
className="h-7 w-7"
onClick={handlePlayPause}
title="Play/Pause (Space)"
aria-label={isCurrentlyPlaying ? 'Pause' : 'Play'}
>
{isCurrentlyPlaying ? <Pause className="h-4 w-4" /> : <Play className="h-4 w-4" />}
</Button>
@@ -745,6 +804,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
className="h-7 w-7"
onClick={handleStop}
disabled={!isCurrentlyPlaying}
aria-label="Stop"
>
<Square className="h-3 w-3" />
</Button>
@@ -762,6 +822,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
className="h-7 w-7"
onClick={handleSplit}
title="Split at playhead (S)"
aria-label="Split at playhead"
>
<Scissors className="h-4 w-4" />
</Button>
@@ -771,6 +832,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
className="h-7 w-7"
onClick={handleDuplicate}
title="Duplicate (Cmd/Ctrl+D)"
aria-label="Duplicate clip"
>
<Copy className="h-4 w-4" />
</Button>
@@ -780,19 +842,75 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
className="h-7 w-7"
onClick={handleDelete}
title="Delete (Delete/Backspace)"
aria-label="Delete clip"
>
<Trash2 className="h-4 w-4" />
</Button>
{hasMultipleVersions && (
<>
<div className="w-px h-4 bg-border mx-1" />
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button
variant="ghost"
className="h-7 gap-1.5 px-2 text-xs"
title="Change version/take"
>
<GalleryVerticalEnd className="h-3.5 w-3.5" />
<span className="max-w-[80px] truncate">
{activeVersionLabel ?? 'default'}
</span>
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="center" className="min-w-[160px]">
{selectedItemVersions.map((version) => {
const isActive = selectedItem?.version_id
? version.id === selectedItem.version_id
: version.is_default;
return (
<DropdownMenuItem
key={version.id}
onClick={() => handleSetVersion(version.id)}
className="gap-2 text-xs"
>
<Check
className={cn('h-3 w-3', isActive ? 'opacity-100' : 'opacity-0')}
/>
<span className="truncate">{version.label}</span>
{version.effects_chain && version.effects_chain.length > 0 && (
<span className="text-muted-foreground ml-auto text-[10px]">
{version.effects_chain.length} fx
</span>
)}
</DropdownMenuItem>
);
})}
</DropdownMenuContent>
</DropdownMenu>
</>
)}
</div>
)}
{/* Zoom controls - right side */}
<div className="flex items-center gap-2">
<span className="text-xs text-muted-foreground">Zoom:</span>
<Button variant="ghost" size="icon" className="h-6 w-6" onClick={handleZoomOut}>
<Button
variant="ghost"
size="icon"
className="h-6 w-6"
onClick={handleZoomOut}
aria-label="Zoom out"
>
<Minus className="h-3 w-3" />
</Button>
<Button variant="ghost" size="icon" className="h-6 w-6" onClick={handleZoomIn}>
<Button
variant="ghost"
size="icon"
className="h-6 w-6"
onClick={handleZoomIn}
aria-label="Zoom in"
>
<Plus className="h-3 w-3" />
</Button>
</div>
@@ -941,6 +1059,7 @@ export function StoryTrackEditor({ storyId, items }: StoryTrackEditorProps) {
<div className="absolute inset-0 top-3">
<ClipWaveform
generationId={item.generation_id}
versionId={item.version_id}
width={clipWidth}
trimStartMs={displayTrimStart}
trimEndMs={displayTrimEnd}
+5 -6
View File
@@ -1,8 +1,7 @@
const isWindows = navigator.userAgent.includes('Windows');
export function TitleBarDragRegion() {
return (
<div
data-tauri-drag-region
className="fixed top-0 left-0 right-0 h-12 z-[9999]"
/>
);
if (isWindows) return null;
return <div data-tauri-drag-region className="fixed top-0 left-0 right-0 h-12 z-[9999]" />;
}
@@ -14,12 +14,7 @@ const MemoizedWaveform = memo(function MemoizedWaveform({
<div className="absolute inset-0 pointer-events-none flex items-center justify-center opacity-30">
<Visualizer audio={audioStream} autoStart strokeColor="#b39a3d">
{({ canvasRef }) => (
<canvas
ref={canvasRef}
width={500}
height={150}
className="w-full h-full"
/>
<canvas ref={canvasRef} width={500} height={150} className="w-full h-full" />
)}
</Visualizer>
</div>
@@ -58,6 +53,7 @@ export function AudioSampleRecording({
// Request microphone access when component mounts
useEffect(() => {
if (!showWaveform) return;
if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) return;
let stream: MediaStream | null = null;
@@ -86,9 +82,7 @@ export function AudioSampleRecording({
<div className="space-y-4">
{!isRecording && !file && (
<div className="relative flex flex-col items-center justify-center gap-4 p-4 border-2 border-dashed rounded-lg min-h-[180px] overflow-hidden">
{showWaveform && audioStream && (
<MemoizedWaveform audioStream={audioStream} />
)}
{showWaveform && audioStream && <MemoizedWaveform audioStream={audioStream} />}
<Button
type="button"
onClick={onStart}
@@ -106,9 +100,7 @@ export function AudioSampleRecording({
{isRecording && (
<div className="relative flex flex-col items-center justify-center gap-4 p-4 border-2 border-accent rounded-lg bg-accent/5 min-h-[180px] overflow-hidden">
{showWaveform && audioStream && (
<MemoizedWaveform audioStream={audioStream} />
)}
{showWaveform && audioStream && <MemoizedWaveform audioStream={audioStream} />}
<div className="relative z-10 flex items-center gap-4">
<div className="flex items-center gap-2">
<div className="h-3 w-3 rounded-full bg-accent animate-pulse" />
@@ -139,7 +131,13 @@ export function AudioSampleRecording({
</div>
<p className="text-sm text-muted-foreground text-center">File: {file.name}</p>
<div className="flex gap-2">
<Button type="button" size="icon" variant="outline" onClick={onPlayPause}>
<Button
type="button"
size="icon"
variant="outline"
onClick={onPlayPause}
aria-label={isPlaying ? 'Pause' : 'Play'}
>
{isPlaying ? <Pause className="h-4 w-4" /> : <Play className="h-4 w-4" />}
</Button>
<Button
@@ -77,7 +77,13 @@ export function AudioSampleSystem({
</div>
<p className="text-sm text-muted-foreground text-center">File: {file.name}</p>
<div className="flex gap-2">
<Button type="button" size="icon" variant="outline" onClick={onPlayPause}>
<Button
type="button"
size="icon"
variant="outline"
onClick={onPlayPause}
aria-label={isPlaying ? 'Pause' : 'Play'}
>
{isPlaying ? <Pause className="h-4 w-4" /> : <Play className="h-4 w-4" />}
</Button>
<Button
@@ -110,6 +110,7 @@ export function AudioSampleUpload({
variant="outline"
onClick={onPlayPause}
disabled={isValidating}
aria-label={isPlaying ? 'Pause' : 'Play'}
>
{isPlaying ? <Pause className="h-4 w-4" /> : <Play className="h-4 w-4" />}
</Button>
@@ -1,4 +1,4 @@
import { Download, Edit, Mic, Trash2 } from 'lucide-react';
import { Download, Edit, Sparkles, Trash2 } from 'lucide-react';
import { useState } from 'react';
import { Badge } from '@/components/ui/badge';
import { Button } from '@/components/ui/button';
@@ -15,29 +15,38 @@ import {
import type { VoiceProfileResponse } from '@/lib/api/types';
import { useDeleteProfile, useExportProfile } from '@/lib/hooks/useProfiles';
import { cn } from '@/lib/utils/cn';
import { useServerStore } from '@/stores/serverStore';
import { useUIStore } from '@/stores/uiStore';
/** Human-readable display names for preset engine badges. */
const ENGINE_DISPLAY_NAMES: Record<string, string> = {
kokoro: 'Kokoro',
qwen_custom_voice: 'CustomVoice',
};
interface ProfileCardProps {
profile: VoiceProfileResponse;
disabled?: boolean;
}
export function ProfileCard({ profile }: ProfileCardProps) {
export function ProfileCard({ profile, disabled }: ProfileCardProps) {
const [deleteDialogOpen, setDeleteDialogOpen] = useState(false);
const [avatarError, setAvatarError] = useState(false);
const deleteProfile = useDeleteProfile();
const exportProfile = useExportProfile();
const setEditingProfileId = useUIStore((state) => state.setEditingProfileId);
const setProfileDialogOpen = useUIStore((state) => state.setProfileDialogOpen);
const selectedProfileId = useUIStore((state) => state.selectedProfileId);
const setSelectedProfileId = useUIStore((state) => state.setSelectedProfileId);
const serverUrl = useServerStore((state) => state.serverUrl);
const isSelected = selectedProfileId === profile.id;
const avatarUrl = profile.avatar_path ? `${serverUrl}/profiles/${profile.id}/avatar` : null;
const handleSelect = () => {
// If disabled but already selected, bounce the selection to re-trigger engine auto-switch
if (disabled && isSelected) {
setSelectedProfileId(null);
setTimeout(() => setSelectedProfileId(profile.id), 0);
return;
}
setSelectedProfileId(isSelected ? null : profile.id);
};
@@ -61,32 +70,36 @@ export function ProfileCard({ profile }: ProfileCardProps) {
exportProfile.mutate(profile.id);
};
const handleKeyDown = (e: React.KeyboardEvent) => {
const target = e.target as HTMLElement;
if (target.closest('button')) return;
if (e.key === 'Enter' || e.key === ' ') {
e.preventDefault();
handleSelect();
}
};
const selectLabel = isSelected
? `${profile.name}, ${profile.language}. Selected as voice for generation.`
: `${profile.name}, ${profile.language}. Select as voice for generation.`;
return (
<>
<Card
className={cn(
'cursor-pointer hover:shadow-md transition-all flex flex-col',
isSelected && 'ring-2 ring-primary shadow-md',
'cursor-pointer transition-all flex flex-col h-[162px]',
disabled ? 'opacity-40 hover:opacity-60' : 'hover:shadow-md',
isSelected && !disabled && 'ring-2 ring-accent shadow-md',
)}
onClick={handleSelect}
tabIndex={0}
role="button"
aria-label={selectLabel}
aria-pressed={isSelected}
onKeyDown={handleKeyDown}
>
<CardHeader className="p-3 pb-2">
<CardTitle className="flex items-center gap-1.5 text-base font-medium">
<div className="h-6 w-6 rounded-full bg-muted flex items-center justify-center shrink-0 overflow-hidden">
{avatarUrl && !avatarError ? (
<img
src={avatarUrl}
alt={`${profile.name} avatar`}
className={cn(
'h-full w-full object-cover transition-all duration-200',
!isSelected && 'grayscale',
)}
onError={() => setAvatarError(true)}
/>
) : (
<Mic className="h-3.5 w-3.5 text-muted-foreground" />
)}
</div>
<CardTitle className="text-base font-medium">
<span className="break-words">{profile.name}</span>
</CardTitle>
</CardHeader>
@@ -94,10 +107,23 @@ export function ProfileCard({ profile }: ProfileCardProps) {
<p className="text-xs text-muted-foreground mb-1.5 line-clamp-2 leading-relaxed">
{profile.description || 'No description'}
</p>
<div className="mb-2">
<div className="mb-2 flex items-center gap-1.5">
<Badge variant="outline" className="text-xs h-5 px-1.5 text-muted-foreground">
{profile.language}
</Badge>
{profile.voice_type === 'preset' && (
<Badge variant="secondary" className="text-xs h-5 px-1.5">
{ENGINE_DISPLAY_NAMES[profile.preset_engine ?? ''] ?? profile.preset_engine}
</Badge>
)}
{profile.voice_type === 'designed' && (
<Badge variant="secondary" className="text-xs h-5 px-1.5">
designed
</Badge>
)}
{profile.effects_chain && profile.effects_chain.length > 0 && (
<Sparkles className="h-3.5 w-3.5 text-accent fill-accent" />
)}
</div>
<div className="flex gap-0.5 justify-end items-end mt-auto">
<CircleButton
+472 -132
View File
@@ -1,8 +1,11 @@
import { zodResolver } from '@hookform/resolvers/zod';
import { Edit2, Mic, Monitor, Upload, X } from 'lucide-react';
import { useQuery } from '@tanstack/react-query';
import { Edit2, Mic, Monitor, Music, Upload, X } from 'lucide-react';
import { useEffect, useRef, useState } from 'react';
import { useForm } from 'react-hook-form';
import * as z from 'zod';
import { EffectsChainEditor } from '@/components/Effects/EffectsChainEditor';
import { Badge } from '@/components/ui/badge';
import { Button } from '@/components/ui/button';
import {
Dialog,
@@ -14,6 +17,7 @@ import {
import {
Form,
FormControl,
FormDescription,
FormField,
FormItem,
FormLabel,
@@ -30,6 +34,8 @@ import {
import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import type { EffectConfig, PresetVoice, VoiceType } from '@/lib/api/types';
import { LANGUAGE_CODES, LANGUAGE_OPTIONS, type LanguageCode } from '@/lib/constants/languages';
import { useAudioPlayer } from '@/lib/hooks/useAudioPlayer';
import { useAudioRecording } from '@/lib/hooks/useAudioRecording';
@@ -37,13 +43,14 @@ import {
useAddSample,
useCreateProfile,
useDeleteAvatar,
useDeleteProfile,
useProfile,
useUpdateProfile,
useUploadAvatar,
} from '@/lib/hooks/useProfiles';
import { useSystemAudioCapture } from '@/lib/hooks/useSystemAudioCapture';
import { useTranscription } from '@/lib/hooks/useTranscription';
import { formatAudioDuration, getAudioDuration } from '@/lib/utils/audio';
import { convertToWav, formatAudioDuration, getAudioDuration } from '@/lib/utils/audio';
import { usePlatform } from '@/platform/PlatformContext';
import { useServerStore } from '@/stores/serverStore';
import { type ProfileFormDraft, useUIStore } from '@/stores/uiStore';
@@ -53,6 +60,16 @@ import { AudioSampleUpload } from './AudioSampleUpload';
import { SampleList } from './SampleList';
const MAX_AUDIO_DURATION_SECONDS = 30;
const PRESET_ONLY_ENGINES = new Set(['kokoro', 'qwen_custom_voice']);
const DEFAULT_ENGINE_OPTIONS = [
{ value: 'qwen', label: 'Qwen3-TTS' },
{ value: 'qwen_custom_voice', label: 'Qwen CustomVoice' },
{ value: 'luxtts', label: 'LuxTTS' },
{ value: 'chatterbox', label: 'Chatterbox' },
{ value: 'chatterbox_turbo', label: 'Chatterbox Turbo' },
{ value: 'tada', label: 'TADA' },
{ value: 'kokoro', label: 'Kokoro 82M' },
] as const;
const baseProfileSchema = z.object({
name: z.string().min(1, 'Name is required').max(100),
@@ -113,18 +130,25 @@ export function ProfileForm() {
const createProfile = useCreateProfile();
const updateProfile = useUpdateProfile();
const addSample = useAddSample();
const deleteProfile = useDeleteProfile();
const uploadAvatar = useUploadAvatar();
const deleteAvatar = useDeleteAvatar();
const transcribe = useTranscription();
const { toast } = useToast();
const [voiceSource, setVoiceSource] = useState<'clone' | 'builtin'>('clone');
const [sampleMode, setSampleMode] = useState<'upload' | 'record' | 'system'>('record');
const [audioDuration, setAudioDuration] = useState<number | null>(null);
const [isValidatingAudio, setIsValidatingAudio] = useState(false);
const [avatarPreview, setAvatarPreview] = useState<string | null>(null);
const [selectedPresetEngine, setSelectedPresetEngine] = useState<string>('kokoro');
const [selectedPresetVoiceId, setSelectedPresetVoiceId] = useState<string>('');
const avatarInputRef = useRef<HTMLInputElement>(null);
const { isPlaying, playPause, cleanup: cleanupAudio } = useAudioPlayer();
const isCreating = !editingProfileId;
const serverUrl = useServerStore((state) => state.serverUrl);
const [profileEffectsChain, setProfileEffectsChain] = useState<EffectConfig[]>([]);
const [effectsDirty, setEffectsDirty] = useState(false);
const [defaultEngine, setDefaultEngine] = useState<string>('');
const form = useForm<ProfileFormValues>({
resolver: zodResolver(profileSchema),
@@ -234,6 +258,26 @@ export function ProfileForm() {
},
});
// Fetch available preset voices for the selected engine
const presetEngineToQuery = isCreating
? selectedPresetEngine
: (editingProfile?.preset_engine ?? '');
const { data: presetVoicesData } = useQuery({
queryKey: ['presetVoices', presetEngineToQuery],
queryFn: () => apiClient.listPresetVoices(presetEngineToQuery),
enabled:
!!presetEngineToQuery &&
((voiceSource === 'builtin' && isCreating) ||
(!isCreating && editingProfile?.voice_type === 'preset')),
});
const presetVoices = presetVoicesData?.voices ?? [];
const isSampleBasedProfile = isCreating
? voiceSource === 'clone'
: editingProfile?.voice_type !== 'preset';
const availableDefaultEngines = DEFAULT_ENGINE_OPTIONS.filter(
(option) => !isSampleBasedProfile || !PRESET_ONLY_ENGINES.has(option.value),
);
// Show recording errors
useEffect(() => {
if (recordingError) {
@@ -280,6 +324,9 @@ export function ProfileForm() {
referenceText: undefined,
avatarFile: undefined,
});
setProfileEffectsChain(editingProfile.effects_chain ?? []);
setEffectsDirty(false);
setDefaultEngine(editingProfile.default_engine ?? '');
} else if (profileFormDraft && open) {
// Restore from draft when opening in create mode
form.reset({
@@ -319,6 +366,24 @@ export function ProfileForm() {
}
}, [editingProfile, profileFormDraft, open, form]);
useEffect(() => {
if (
defaultEngine &&
!availableDefaultEngines.some((option) => option.value === defaultEngine)
) {
setDefaultEngine('');
}
}, [availableDefaultEngines, defaultEngine]);
useEffect(() => {
if (!selectedPresetVoiceId) {
return;
}
if (!presetVoices.some((voice: PresetVoice) => voice.voice_id === selectedPresetVoiceId)) {
setSelectedPresetVoiceId('');
}
}, [presetVoices, selectedPresetVoiceId]);
async function handleTranscribe() {
const file = form.getValues('sampleFile');
if (!file) {
@@ -408,13 +473,14 @@ export function ProfileForm() {
async function onSubmit(data: ProfileFormValues) {
try {
if (editingProfileId) {
// Editing: just update profile
// Editing: update profile
await updateProfile.mutateAsync({
profileId: editingProfileId,
data: {
name: data.name,
description: data.description,
language: data.language,
default_engine: defaultEngine || undefined,
},
});
@@ -435,12 +501,72 @@ export function ProfileForm() {
}
}
// Save effects chain if changed
if (effectsDirty) {
try {
await apiClient.updateProfileEffects(
editingProfileId,
profileEffectsChain.length > 0 ? profileEffectsChain : null,
);
} catch (fxError) {
toast({
title: 'Effects update failed',
description:
fxError instanceof Error ? fxError.message : 'Failed to save effects chain',
variant: 'destructive',
});
return;
}
}
toast({
title: 'Voice updated',
description: `"${data.name}" has been updated successfully.`,
});
} else if (voiceSource === 'builtin') {
// Creating preset profile from built-in voice
if (!selectedPresetVoiceId) {
toast({
title: 'No voice selected',
description: 'Please select a built-in voice.',
variant: 'destructive',
});
return;
}
const profile = await createProfile.mutateAsync({
name: data.name,
description: data.description,
language: data.language,
voice_type: 'preset' as VoiceType,
preset_engine: selectedPresetEngine,
preset_voice_id: selectedPresetVoiceId,
default_engine: selectedPresetEngine,
});
// Handle avatar upload if provided
if (data.avatarFile) {
try {
await uploadAvatar.mutateAsync({
profileId: profile.id,
file: data.avatarFile,
});
} catch (avatarError) {
toast({
title: 'Avatar upload failed',
description:
avatarError instanceof Error ? avatarError.message : 'Failed to upload avatar',
variant: 'destructive',
});
}
}
toast({
title: 'Profile created',
description: `"${data.name}" has been created with a built-in voice.`,
});
} else {
// Creating: require sample file and reference text
// Creating cloned profile: require sample file and reference text
const sampleFile = form.getValues('sampleFile');
const referenceText = form.getValues('referenceText');
@@ -503,12 +629,26 @@ export function ProfileForm() {
name: data.name,
description: data.description,
language: data.language,
default_engine: defaultEngine || undefined,
});
// Convert non-WAV uploads to WAV so the backend can always use soundfile.
// Recorded audio is already WAV (from useAudioRecording's convertToWav call).
let fileToUpload: File = sampleFile;
if (!sampleFile.type.includes('wav') && !sampleFile.name.toLowerCase().endsWith('.wav')) {
try {
const wavBlob = await convertToWav(sampleFile);
const wavName = sampleFile.name.replace(/\.[^.]+$/, '.wav');
fileToUpload = new File([wavBlob], wavName, { type: 'audio/wav' });
} catch {
// If browser can't decode the format, send the original and let the backend try.
}
}
try {
await addSample.mutateAsync({
profileId: profile.id,
file: sampleFile,
file: fileToUpload,
referenceText: referenceText,
});
@@ -534,12 +674,32 @@ export function ProfileForm() {
description: `"${data.name}" has been created with a sample.`,
});
} catch (sampleError) {
// Profile was created but sample failed - still show error
let rollbackSucceeded = false;
try {
await deleteProfile.mutateAsync(profile.id);
rollbackSucceeded = true;
} catch (rollbackError) {
toast({
title: 'Rollback failed',
description:
rollbackError instanceof Error
? rollbackError.message
: 'Created profile could not be removed after sample upload failure.',
variant: 'destructive',
});
}
toast({
title: 'Failed to add sample',
description: `Profile "${data.name}" was created, but failed to add sample: ${sampleError instanceof Error ? sampleError.message : 'Unknown error'}`,
description:
sampleError instanceof Error
? `${sampleError.message}${rollbackSucceeded ? ' The profile was rolled back.' : ''}`
: rollbackSucceeded
? 'Failed to add sample. The profile was rolled back.'
: 'Failed to add sample.',
variant: 'destructive',
});
return;
}
}
@@ -604,16 +764,16 @@ export function ProfileForm() {
return (
<Dialog open={open} onOpenChange={handleOpenChange}>
<DialogContent className="max-w-none w-screen h-screen left-0 top-0 translate-x-0 translate-y-0 rounded-none p-6 overflow-y-auto">
<div className="max-w-5xl max-h-[85vh] mx-auto my-auto w-full flex flex-col">
<DialogContent className="max-w-none w-screen h-screen left-0 top-0 translate-x-0 translate-y-0 rounded-none p-6 overflow-hidden">
<div className="max-w-5xl h-[85vh] mx-auto my-auto w-full flex flex-col overflow-hidden">
<DialogHeader>
<DialogTitle className="text-2xl">
{editingProfileId ? 'Edit Voice' : 'Clone voice'}
{editingProfileId ? 'Edit Voice' : 'Create Voice'}
</DialogTitle>
<DialogDescription>
{editingProfileId
? 'Update your voice profile details and manage samples.'
: 'Create a new voice profile with an audio sample to clone the voice.'}
: 'Create a new voice profile from an audio sample or a built-in voice.'}
</DialogDescription>
{isCreating && profileFormDraft && (
<div className="flex items-center gap-2 pt-2">
@@ -644,143 +804,276 @@ export function ProfileForm() {
<Form {...form}>
<form onSubmit={form.handleSubmit(onSubmit)} className="flex-1 min-h-0 flex flex-col">
<div className="grid gap-6 grid-cols-2 flex-1 overflow-y-auto min-h-0">
<div className="grid gap-6 grid-cols-2 flex-1 min-h-0 overflow-hidden">
{/* Left column: Sample management */}
<div className="space-y-4 border-r pr-6">
<div className="space-y-4 border-r pr-6 overflow-y-auto min-h-0">
{isCreating ? (
<>
<Tabs
className="pt-4"
value={sampleMode}
onValueChange={(v) => {
const newMode = v as 'upload' | 'record' | 'system';
// Cancel any active recordings when switching modes
if (isRecording && newMode !== 'record') {
cancelRecording();
}
if (isSystemRecording && newMode !== 'system') {
cancelSystemRecording();
}
setSampleMode(newMode);
}}
>
<TabsList
className={`grid w-full ${platform.metadata.isTauri && isSystemAudioSupported ? 'grid-cols-3' : 'grid-cols-2'}`}
>
<TabsTrigger value="upload" className="flex items-center gap-2">
<Upload className="h-4 w-4 shrink-0" />
Upload
</TabsTrigger>
<TabsTrigger value="record" className="flex items-center gap-2">
<Mic className="h-4 w-4 shrink-0" />
Record
</TabsTrigger>
{platform.metadata.isTauri && isSystemAudioSupported && (
<TabsTrigger value="system" className="flex items-center gap-2">
<Monitor className="h-4 w-4 shrink-0" />
System Audio
</TabsTrigger>
)}
</TabsList>
{/* Voice source selector */}
<div className="flex pt-4 pb-2">
<div className="inline-flex rounded-lg border border-border p-0.5 bg-muted/50">
<button
type="button"
onClick={() => setVoiceSource('clone')}
className={`inline-flex items-center gap-2 px-3 py-1.5 text-sm rounded-md transition-colors ${
voiceSource === 'clone'
? 'bg-accent text-accent-foreground shadow-sm'
: 'text-muted-foreground hover:text-foreground'
}`}
>
<Mic className="h-3.5 w-3.5" />
Clone from audio
</button>
<button
type="button"
onClick={() => setVoiceSource('builtin')}
className={`inline-flex items-center gap-2 px-3 py-1.5 text-sm rounded-md transition-colors ${
voiceSource === 'builtin'
? 'bg-accent text-accent-foreground shadow-sm'
: 'text-muted-foreground hover:text-foreground'
}`}
>
<Music className="h-3.5 w-3.5" />
Built-in voice
</button>
</div>
</div>
<TabsContent value="upload" className="space-y-4">
<FormField
control={form.control}
name="sampleFile"
render={({ field: { onChange, name } }) => (
<AudioSampleUpload
file={selectedFile}
onFileChange={onChange}
onTranscribe={handleTranscribe}
onPlayPause={handlePlayPause}
isPlaying={isPlaying}
isValidating={isValidatingAudio}
isTranscribing={transcribe.isPending}
isDisabled={
audioDuration !== null &&
audioDuration > MAX_AUDIO_DURATION_SECONDS
}
fieldName={name}
/>
)}
/>
</TabsContent>
{voiceSource === 'builtin' ? (
<div className="space-y-4">
<FormDescription>
Choose a pre-built voice. These don't require an audio sample.
</FormDescription>
<TabsContent value="record" className="space-y-4">
<FormField
control={form.control}
name="sampleFile"
render={() => (
<AudioSampleRecording
file={selectedFile}
isRecording={isRecording}
duration={duration}
onStart={startRecording}
onStop={stopRecording}
onCancel={handleCancelRecording}
onTranscribe={handleTranscribe}
onPlayPause={handlePlayPause}
isPlaying={isPlaying}
isTranscribing={transcribe.isPending}
/>
)}
/>
</TabsContent>
{platform.metadata.isTauri && isSystemAudioSupported && (
<TabsContent value="system" className="space-y-4">
<FormField
control={form.control}
name="sampleFile"
render={() => (
<AudioSampleSystem
file={selectedFile}
isRecording={isSystemRecording}
duration={systemDuration}
onStart={startSystemRecording}
onStop={stopSystemRecording}
onCancel={handleCancelRecording}
onTranscribe={handleTranscribe}
onPlayPause={handlePlayPause}
isPlaying={isPlaying}
isTranscribing={transcribe.isPending}
/>
)}
/>
</TabsContent>
)}
</Tabs>
<FormField
control={form.control}
name="referenceText"
render={({ field }) => (
{/* Engine selector */}
<FormItem>
<FormLabel>Reference Text</FormLabel>
<FormControl>
<Textarea
placeholder="Enter the exact text spoken in the audio..."
className="min-h-[100px]"
{...field}
/>
</FormControl>
<FormMessage />
<FormLabel>Engine</FormLabel>
<Select
value={selectedPresetEngine}
onValueChange={setSelectedPresetEngine}
>
<FormControl>
<SelectTrigger>
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
<SelectItem value="kokoro">Kokoro 82M</SelectItem>
<SelectItem value="qwen_custom_voice">Qwen CustomVoice</SelectItem>
</SelectContent>
</Select>
</FormItem>
)}
/>
{/* Voice picker */}
<FormItem>
<FormLabel>Voice</FormLabel>
<div className="grid grid-cols-2 gap-1.5 max-h-[340px] overflow-y-auto pr-1">
{presetVoices.map((voice: PresetVoice) => (
<button
key={voice.voice_id}
type="button"
onClick={() => {
setSelectedPresetVoiceId(voice.voice_id);
// Auto-set language from voice
if (voice.language) {
form.setValue('language', voice.language as LanguageCode);
}
}}
className={`text-left px-3 py-2 rounded-md border text-sm transition-colors ${
selectedPresetVoiceId === voice.voice_id
? 'border-accent bg-accent/10 text-accent-foreground'
: 'border-border hover:bg-muted'
}`}
>
<div className="font-medium">{voice.name}</div>
<div className="flex gap-1.5 mt-0.5">
<Badge variant="outline" className="text-[10px] h-4 px-1">
{voice.gender}
</Badge>
<Badge variant="outline" className="text-[10px] h-4 px-1">
{voice.language}
</Badge>
</div>
</button>
))}
</div>
</FormItem>
</div>
) : (
<>
<Tabs
className="pt-0"
value={sampleMode}
onValueChange={(v) => {
const newMode = v as 'upload' | 'record' | 'system';
// Cancel any active recordings when switching modes
if (isRecording && newMode !== 'record') {
cancelRecording();
}
if (isSystemRecording && newMode !== 'system') {
cancelSystemRecording();
}
setSampleMode(newMode);
}}
>
<TabsList
className={`grid w-full ${platform.metadata.isTauri && isSystemAudioSupported ? 'grid-cols-3' : 'grid-cols-2'}`}
>
<TabsTrigger value="upload" className="flex items-center gap-2">
<Upload className="h-4 w-4 shrink-0" />
Upload
</TabsTrigger>
<TabsTrigger value="record" className="flex items-center gap-2">
<Mic className="h-4 w-4 shrink-0" />
Record
</TabsTrigger>
{platform.metadata.isTauri && isSystemAudioSupported && (
<TabsTrigger value="system" className="flex items-center gap-2">
<Monitor className="h-4 w-4 shrink-0" />
System Audio
</TabsTrigger>
)}
</TabsList>
<TabsContent value="upload" className="space-y-4">
<FormField
control={form.control}
name="sampleFile"
render={({ field: { onChange, name } }) => (
<AudioSampleUpload
file={selectedFile}
onFileChange={onChange}
onTranscribe={handleTranscribe}
onPlayPause={handlePlayPause}
isPlaying={isPlaying}
isValidating={isValidatingAudio}
isTranscribing={transcribe.isPending}
isDisabled={
audioDuration !== null &&
audioDuration > MAX_AUDIO_DURATION_SECONDS
}
fieldName={name}
/>
)}
/>
</TabsContent>
<TabsContent value="record" className="space-y-4">
<FormField
control={form.control}
name="sampleFile"
render={() => (
<AudioSampleRecording
file={selectedFile}
isRecording={isRecording}
duration={duration}
onStart={startRecording}
onStop={stopRecording}
onCancel={handleCancelRecording}
onTranscribe={handleTranscribe}
onPlayPause={handlePlayPause}
isPlaying={isPlaying}
isTranscribing={transcribe.isPending}
/>
)}
/>
</TabsContent>
{platform.metadata.isTauri && isSystemAudioSupported && (
<TabsContent value="system" className="space-y-4">
<FormField
control={form.control}
name="sampleFile"
render={() => (
<AudioSampleSystem
file={selectedFile}
isRecording={isSystemRecording}
duration={systemDuration}
onStart={startSystemRecording}
onStop={stopSystemRecording}
onCancel={handleCancelRecording}
onTranscribe={handleTranscribe}
onPlayPause={handlePlayPause}
isPlaying={isPlaying}
isTranscribing={transcribe.isPending}
/>
)}
/>
</TabsContent>
)}
</Tabs>
<FormField
control={form.control}
name="referenceText"
render={({ field }) => (
<FormItem>
<FormLabel>Reference Text</FormLabel>
<FormControl>
<Textarea
placeholder="Enter the exact text spoken in the audio..."
className="min-h-[100px]"
{...field}
/>
</FormControl>
<FormMessage />
</FormItem>
)}
/>
</>
)}
</>
) : (
// Show sample list when editing
editingProfileId && (
// Editing mode
editingProfileId &&
editingProfile &&
(editingProfile.voice_type === 'preset' ? (
<div className="space-y-4 pt-4">
<div className="rounded-lg border border-border p-4 space-y-3">
<div className="text-sm font-medium text-muted-foreground">
Built-in Voice
</div>
<div className="flex items-center gap-3">
<div className="text-lg font-semibold">
{presetVoices.find(
(v: PresetVoice) => v.voice_id === editingProfile.preset_voice_id,
)?.name ?? editingProfile.preset_voice_id}
</div>
<Badge variant="secondary" className="text-xs">
{editingProfile.preset_engine}
</Badge>
</div>
{(() => {
const voice = presetVoices.find(
(v: PresetVoice) => v.voice_id === editingProfile.preset_voice_id,
);
return voice ? (
<div className="flex gap-1.5">
<Badge variant="outline" className="text-xs">
{voice.gender}
</Badge>
<Badge variant="outline" className="text-xs">
{voice.language}
</Badge>
</div>
) : null;
})()}
</div>
<p className="text-xs text-muted-foreground">
This profile uses a built-in voice. The voice cannot be changed after
creation.
</p>
</div>
) : (
<div>
<SampleList profileId={editingProfileId} />
</div>
)
))
)}
</div>
{/* Right column: Profile info */}
<div className="space-y-4">
<div className="space-y-4 overflow-y-auto min-h-0">
{/* Avatar Upload */}
<FormField
control={form.control}
@@ -885,6 +1178,53 @@ export function ProfileForm() {
</FormItem>
)}
/>
<FormItem>
<FormLabel>Default Engine</FormLabel>
<Select
value={defaultEngine || '_none'}
onValueChange={(v) => {
setDefaultEngine(v === '_none' ? '' : v);
}}
disabled={
voiceSource === 'builtin' || editingProfile?.voice_type === 'preset'
}
>
<FormControl>
<SelectTrigger>
<SelectValue placeholder="No preference" />
</SelectTrigger>
</FormControl>
<SelectContent>
<SelectItem value="_none">No preference</SelectItem>
{availableDefaultEngines.map((option) => (
<SelectItem key={option.value} value={option.value}>
{option.label}
</SelectItem>
))}
</SelectContent>
</Select>
<p className="text-xs text-muted-foreground">
Auto-selects this engine when the profile is chosen.
</p>
</FormItem>
{editingProfileId && (
<div className="space-y-2">
<FormLabel>Default Effects</FormLabel>
<p className="text-xs text-muted-foreground">
Effects applied automatically to all new generations with this voice.
</p>
<EffectsChainEditor
value={profileEffectsChain}
onChange={(chain) => {
setProfileEffectsChain(chain);
setEffectsDirty(true);
}}
compact
/>
</div>
)}
</div>
</div>
@@ -1,4 +1,5 @@
import { Mic, Sparkles } from 'lucide-react';
import { Info, Mic, Sparkles } from 'lucide-react';
import { useEffect, useRef } from 'react';
import { Button } from '@/components/ui/button';
import { Card, CardContent } from '@/components/ui/card';
import { useProfiles } from '@/lib/hooks/useProfiles';
@@ -6,9 +7,36 @@ import { useUIStore } from '@/stores/uiStore';
import { ProfileCard } from './ProfileCard';
import { ProfileForm } from './ProfileForm';
/** Engines that use preset (built-in) voices instead of cloned profiles. */
const PRESET_ENGINES = new Set(['kokoro', 'qwen_custom_voice']);
export function ProfileList() {
const { data: profiles, isLoading, error } = useProfiles();
const setDialogOpen = useUIStore((state) => state.setProfileDialogOpen);
const selectedEngine = useUIStore((state) => state.selectedEngine);
const selectedProfileId = useUIStore((state) => state.selectedProfileId);
const cardRefs = useRef<Map<string, HTMLDivElement>>(new Map());
// Scroll to the selected profile after engine/sort changes
useEffect(() => {
if (!selectedProfileId) return;
let timeoutId: ReturnType<typeof setTimeout> | null = null;
const rafId = requestAnimationFrame(() => {
const el = cardRefs.current.get(selectedProfileId);
if (!el) return;
// Temporarily apply scroll-margin so it doesn't land flush at the top
el.style.scrollMarginTop = '180px';
el.scrollIntoView({ behavior: 'smooth', block: 'nearest', inline: 'nearest' });
timeoutId = setTimeout(() => {
el.style.scrollMarginTop = '';
}, 500);
});
return () => {
cancelAnimationFrame(rafId);
if (timeoutId) clearTimeout(timeoutId);
};
}, [selectedProfileId, selectedEngine]);
if (isLoading) {
return null;
@@ -23,6 +51,20 @@ export function ProfileList() {
}
const allProfiles = profiles || [];
const isPresetEngine = PRESET_ENGINES.has(selectedEngine);
/** Whether a profile is supported by the currently selected engine. */
const isSupported = (p: (typeof allProfiles)[number]) =>
isPresetEngine
? p.voice_type === 'preset' && p.preset_engine === selectedEngine
: p.voice_type !== 'preset';
// Sort so supported profiles come first
const sortedProfiles = [...allProfiles].sort(
(a, b) => (isSupported(a) ? 0 : 1) - (isSupported(b) ? 0 : 1),
);
const hasUnsupported = sortedProfiles.some((p) => !isSupported(p));
return (
<div className="flex flex-col">
@@ -41,10 +83,25 @@ export function ProfileList() {
</CardContent>
</Card>
) : (
<div className="grid gap-4 grid-cols-3 auto-rows-auto p-1 pb-[150px]">
{allProfiles.map((profile) => (
<ProfileCard key={profile.id} profile={profile} />
<div className="flex gap-4 overflow-x-auto p-1 pb-1 lg:grid lg:grid-cols-3 lg:auto-rows-auto lg:overflow-x-visible lg:pb-[150px]">
{sortedProfiles.map((profile) => (
<div
key={profile.id}
className="shrink-0 w-[200px] lg:w-auto lg:shrink"
ref={(el) => {
if (el) cardRefs.current.set(profile.id, el);
else cardRefs.current.delete(profile.id);
}}
>
<ProfileCard profile={profile} disabled={!isSupported(profile)} />
</div>
))}
{hasUnsupported && (
<div className="col-span-full flex items-center gap-2 text-xs text-muted-foreground py-2">
<Info className="h-3.5 w-3.5 shrink-0" />
<span>Only supported voice profiles can be selected for the current model.</span>
</div>
)}
</div>
)}
</div>
@@ -2,6 +2,14 @@ import { Check, Edit, Pause, Play, Plus, Trash2, Volume2, X } from 'lucide-react
import { useEffect, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import { CircleButton } from '@/components/ui/circle-button';
import {
Dialog,
DialogContent,
DialogDescription,
DialogFooter,
DialogHeader,
DialogTitle,
} from '@/components/ui/dialog';
import { Slider } from '@/components/ui/slider';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
@@ -94,6 +102,7 @@ function MiniSamplePlayer({ audioUrl }: MiniSamplePlayerProps) {
className="h-7 w-7 shrink-0"
onClick={handlePlayPause}
disabled={isLoading}
aria-label={isPlaying ? 'Pause sample' : 'Play sample'}
>
{isPlaying ? <Pause className="h-3.5 w-3.5" /> : <Play className="h-3.5 w-3.5 ml-0.5" />}
</Button>
@@ -105,6 +114,8 @@ function MiniSamplePlayer({ audioUrl }: MiniSamplePlayerProps) {
max={100}
step={0.1}
className="flex-1"
aria-label="Sample playback position"
aria-valuetext={`${formatAudioDuration(currentTime)} of ${formatAudioDuration(duration)}`}
/>
<div className="flex items-center gap-1 text-xs text-muted-foreground shrink-0 min-w-[70px]">
<span className="font-mono">{formatAudioDuration(currentTime)}</span>
@@ -120,6 +131,7 @@ function MiniSamplePlayer({ audioUrl }: MiniSamplePlayerProps) {
className="h-7 w-7 shrink-0"
onClick={handleStop}
title="Stop"
aria-label="Stop playback"
>
<X className="h-3.5 w-3.5" />
</Button>
@@ -140,10 +152,19 @@ export function SampleList({ profileId }: SampleListProps) {
const [uploadOpen, setUploadOpen] = useState(false);
const [editingSampleId, setEditingSampleId] = useState<string | null>(null);
const [editedText, setEditedText] = useState<string>('');
const [deleteDialogOpen, setDeleteDialogOpen] = useState(false);
const [sampleToDelete, setSampleToDelete] = useState<string | null>(null);
const handleDelete = (sampleId: string) => {
if (confirm('Are you sure you want to delete this sample?')) {
deleteSample.mutate(sampleId);
const handleDeleteClick = (sampleId: string) => {
setSampleToDelete(sampleId);
setDeleteDialogOpen(true);
};
const handleDeleteConfirm = () => {
if (sampleToDelete) {
deleteSample.mutate(sampleToDelete);
setDeleteDialogOpen(false);
setSampleToDelete(null);
}
};
@@ -268,7 +289,7 @@ export function SampleList({ profileId }: SampleListProps) {
<CircleButton
icon={Trash2}
title="Delete sample"
onClick={() => handleDelete(sample.id)}
onClick={() => handleDeleteClick(sample.id)}
disabled={deleteSample.isPending}
/>
</div>
@@ -306,6 +327,35 @@ export function SampleList({ profileId }: SampleListProps) {
</p>
<SampleUpload profileId={profileId} open={uploadOpen} onOpenChange={setUploadOpen} />
<Dialog open={deleteDialogOpen} onOpenChange={setDeleteDialogOpen}>
<DialogContent>
<DialogHeader>
<DialogTitle>Delete Sample</DialogTitle>
<DialogDescription>
Are you sure you want to delete this audio sample? This action cannot be undone.
</DialogDescription>
</DialogHeader>
<DialogFooter>
<Button
variant="outline"
onClick={() => {
setDeleteDialogOpen(false);
setSampleToDelete(null);
}}
>
Cancel
</Button>
<Button
variant="destructive"
onClick={handleDeleteConfirm}
disabled={deleteSample.isPending}
>
{deleteSample.isPending ? 'Deleting...' : 'Delete'}
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
</div>
);
}
@@ -0,0 +1,340 @@
import { zodResolver } from '@hookform/resolvers/zod';
import { Edit2, Mic, X } from 'lucide-react';
import { useEffect, useRef, useState } from 'react';
import { useForm } from 'react-hook-form';
import * as z from 'zod';
import { EffectsChainEditor } from '@/components/Effects/EffectsChainEditor';
import { Button } from '@/components/ui/button';
import {
Form,
FormControl,
FormField,
FormItem,
FormLabel,
FormMessage,
} from '@/components/ui/form';
import { Input } from '@/components/ui/input';
import {
Select,
SelectContent,
SelectItem,
SelectTrigger,
SelectValue,
} from '@/components/ui/select';
import { Textarea } from '@/components/ui/textarea';
import { useToast } from '@/components/ui/use-toast';
import { SampleList } from '@/components/VoiceProfiles/SampleList';
import { apiClient } from '@/lib/api/client';
import type { EffectConfig } from '@/lib/api/types';
import { LANGUAGE_CODES, LANGUAGE_OPTIONS, type LanguageCode } from '@/lib/constants/languages';
import { BOTTOM_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import {
useDeleteAvatar,
useProfile,
useUpdateProfile,
useUploadAvatar,
} from '@/lib/hooks/useProfiles';
import { cn } from '@/lib/utils/cn';
import { usePlayerStore } from '@/stores/playerStore';
import { useServerStore } from '@/stores/serverStore';
const profileSchema = z.object({
name: z.string().min(1, 'Name is required').max(100),
description: z.string().max(500).optional(),
language: z.enum(LANGUAGE_CODES as [LanguageCode, ...LanguageCode[]]),
});
type ProfileFormValues = z.infer<typeof profileSchema>;
interface VoiceInspectorProps {
profileId: string;
}
export function VoiceInspector({ profileId }: VoiceInspectorProps) {
const { data: profile } = useProfile(profileId);
const audioUrl = usePlayerStore((state) => state.audioUrl);
const isPlayerVisible = !!audioUrl;
const updateProfile = useUpdateProfile();
const uploadAvatar = useUploadAvatar();
const deleteAvatar = useDeleteAvatar();
const serverUrl = useServerStore((state) => state.serverUrl);
const { toast } = useToast();
const [avatarPreview, setAvatarPreview] = useState<string | null>(null);
const [avatarError, setAvatarError] = useState(false);
const avatarInputRef = useRef<HTMLInputElement>(null);
const [effectsChain, setEffectsChain] = useState<EffectConfig[]>([]);
const [effectsDirty, setEffectsDirty] = useState(false);
const form = useForm<ProfileFormValues>({
resolver: zodResolver(profileSchema),
defaultValues: {
name: '',
description: '',
language: 'en',
},
});
// Populate form when profile loads
useEffect(() => {
if (profile) {
form.reset({
name: profile.name,
description: profile.description || '',
language: profile.language as LanguageCode,
});
setEffectsChain(profile.effects_chain ?? []);
setEffectsDirty(false);
}
}, [profile, form]);
// Avatar preview
useEffect(() => {
if (profile?.avatar_path) {
setAvatarPreview(`${serverUrl}/profiles/${profile.id}/avatar`);
} else {
setAvatarPreview(null);
}
setAvatarError(false);
}, [profile, serverUrl]);
function handleAvatarFileChange(e: React.ChangeEvent<HTMLInputElement>) {
const file = e.target.files?.[0];
if (!file) return;
if (!file.type.startsWith('image/')) {
toast({
title: 'Invalid file type',
description: 'Please select PNG, JPG, or WebP',
variant: 'destructive',
});
return;
}
if (file.size > 5 * 1024 * 1024) {
toast({
title: 'File too large',
description: 'Image must be less than 5MB',
variant: 'destructive',
});
return;
}
// Upload immediately
uploadAvatar.mutate(
{ profileId, file },
{
onSuccess: () => {
setAvatarPreview(URL.createObjectURL(file));
toast({ title: 'Avatar updated' });
},
onError: (err) => {
toast({
title: 'Avatar upload failed',
description: err instanceof Error ? err.message : 'Unknown error',
variant: 'destructive',
});
},
},
);
}
async function handleRemoveAvatar() {
if (profile?.avatar_path) {
try {
await deleteAvatar.mutateAsync(profileId);
toast({ title: 'Avatar removed' });
} catch (err) {
toast({
title: 'Failed to remove avatar',
description: err instanceof Error ? err.message : 'Unknown error',
variant: 'destructive',
});
}
}
setAvatarPreview(null);
if (avatarInputRef.current) avatarInputRef.current.value = '';
}
async function onSubmit(data: ProfileFormValues) {
try {
await updateProfile.mutateAsync({
profileId,
data: {
name: data.name,
description: data.description,
language: data.language,
},
});
if (effectsDirty) {
try {
await apiClient.updateProfileEffects(
profileId,
effectsChain.length > 0 ? effectsChain : null,
);
setEffectsDirty(false);
} catch (fxError) {
toast({
title: 'Effects update failed',
description: fxError instanceof Error ? fxError.message : 'Failed to save effects',
variant: 'destructive',
});
return;
}
}
toast({ title: 'Voice updated', description: `"${data.name}" saved.` });
} catch (error) {
toast({
title: 'Error',
description: error instanceof Error ? error.message : 'Failed to save profile',
variant: 'destructive',
});
}
}
if (!profile) {
return (
<div className="flex items-center justify-center h-full text-muted-foreground text-sm">
Loading...
</div>
);
}
const isDirty = form.formState.isDirty || effectsDirty;
return (
<div className="h-full flex flex-col overflow-hidden">
<div className={cn('flex-1 overflow-y-auto', isPlayerVisible && BOTTOM_SAFE_AREA_PADDING)}>
<Form {...form}>
<form onSubmit={form.handleSubmit(onSubmit)} className="space-y-0">
{/* Avatar */}
<div className="flex justify-center pt-5 pb-3">
<div className="relative group">
<div className="h-20 w-20 rounded-full bg-muted flex items-center justify-center shrink-0 overflow-hidden border-2 border-border">
{avatarPreview && !avatarError ? (
<img
src={avatarPreview}
alt={profile.name}
className="h-full w-full object-cover"
onError={() => setAvatarError(true)}
/>
) : (
<Mic className="h-8 w-8 text-muted-foreground" />
)}
</div>
<button
type="button"
onClick={() => avatarInputRef.current?.click()}
className="absolute inset-0 rounded-full bg-accent/60 opacity-0 group-hover:opacity-100 transition-opacity flex items-center justify-center cursor-pointer"
>
<Edit2 className="h-5 w-5 text-accent-foreground" />
</button>
{avatarPreview && (
<button
type="button"
onClick={handleRemoveAvatar}
disabled={deleteAvatar.isPending}
className="absolute bottom-0 right-0 h-5 w-5 rounded-full bg-background/60 backdrop-blur-sm text-muted-foreground flex items-center justify-center hover:bg-background/80 hover:text-foreground transition-colors shadow-sm border border-border/50"
>
<X className="h-3 w-3" />
</button>
)}
</div>
<input
ref={avatarInputRef}
type="file"
accept="image/png,image/jpeg,image/webp"
onChange={handleAvatarFileChange}
className="hidden"
/>
</div>
{/* Fields */}
<div className="space-y-3 px-5">
<FormField
control={form.control}
name="name"
render={({ field }) => (
<FormItem>
<FormLabel>Name</FormLabel>
<FormControl>
<Input placeholder="My Voice" {...field} />
</FormControl>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name="description"
render={({ field }) => (
<FormItem>
<FormLabel>Description</FormLabel>
<FormControl>
<Textarea placeholder="Describe this voice..." rows={2} {...field} />
</FormControl>
<FormMessage />
</FormItem>
)}
/>
<FormField
control={form.control}
name="language"
render={({ field }) => (
<FormItem>
<FormLabel>Language</FormLabel>
<Select onValueChange={field.onChange} value={field.value}>
<FormControl>
<SelectTrigger>
<SelectValue />
</SelectTrigger>
</FormControl>
<SelectContent>
{LANGUAGE_OPTIONS.map((lang) => (
<SelectItem key={lang.value} value={lang.value}>
{lang.label}
</SelectItem>
))}
</SelectContent>
</Select>
<FormMessage />
</FormItem>
)}
/>
{/* Effects */}
<div className="space-y-2">
<FormLabel>Default Effects</FormLabel>
<p className="text-xs text-muted-foreground">
Applied automatically to new generations with this voice.
</p>
<EffectsChainEditor
value={effectsChain}
onChange={(chain) => {
setEffectsChain(chain);
setEffectsDirty(true);
}}
compact
/>
</div>
{/* Save */}
{isDirty && (
<Button type="submit" className="w-full" disabled={updateProfile.isPending}>
{updateProfile.isPending ? 'Saving...' : 'Save Changes'}
</Button>
)}
</div>
{/* Samples */}
<div className="px-5 pb-5">
<SampleList profileId={profileId} />
</div>
</form>
</Form>
</div>
</div>
);
}
+144 -116
View File
@@ -1,13 +1,9 @@
import { useQuery, useQueryClient } from '@tanstack/react-query';
import { Edit, MoreHorizontal, Plus, Trash2, Mic } from 'lucide-react';
import { useMemo, useRef } from 'react';
import { Mic, Plus, Search, Sparkles } from 'lucide-react';
import { useEffect, useMemo, useRef, useState } from 'react';
import { Button } from '@/components/ui/button';
import {
DropdownMenu,
DropdownMenuContent,
DropdownMenuItem,
DropdownMenuTrigger,
} from '@/components/ui/dropdown-menu';
import { Input } from '@/components/ui/input';
import { MultiSelect } from '@/components/ui/multi-select';
import {
Table,
@@ -21,33 +17,46 @@ import { ProfileForm } from '@/components/VoiceProfiles/ProfileForm';
import { apiClient } from '@/lib/api/client';
import type { VoiceProfileResponse } from '@/lib/api/types';
import { BOTTOM_SAFE_AREA_PADDING } from '@/lib/constants/ui';
import { useHistory } from '@/lib/hooks/useHistory';
import { useDeleteProfile, useProfileSamples, useProfiles } from '@/lib/hooks/useProfiles';
import { useProfiles } from '@/lib/hooks/useProfiles';
import { cn } from '@/lib/utils/cn';
import { usePlayerStore } from '@/stores/playerStore';
import { useServerStore } from '@/stores/serverStore';
import { useUIStore } from '@/stores/uiStore';
import { VoiceInspector } from './VoiceInspector';
export function VoicesTab() {
const { data: profiles, isLoading } = useProfiles();
const { data: historyData } = useHistory({ limit: 1000 });
const queryClient = useQueryClient();
const setDialogOpen = useUIStore((state) => state.setProfileDialogOpen);
const setEditingProfileId = useUIStore((state) => state.setEditingProfileId);
const deleteProfile = useDeleteProfile();
const selectedVoiceId = useUIStore((state) => state.selectedVoiceId);
const setSelectedVoiceId = useUIStore((state) => state.setSelectedVoiceId);
const scrollRef = useRef<HTMLDivElement>(null);
const audioUrl = usePlayerStore((state) => state.audioUrl);
const isPlayerVisible = !!audioUrl;
const [search, setSearch] = useState('');
// Get generation counts per profile
const generationCounts = useMemo(() => {
const counts: Record<string, number> = {};
if (historyData?.items) {
historyData.items.forEach((item) => {
counts[item.profile_id] = (counts[item.profile_id] || 0) + 1;
});
const filteredProfiles = useMemo(() => {
if (!profiles) return [];
if (!search.trim()) return profiles;
const q = search.toLowerCase();
return profiles.filter(
(p) =>
p.name.toLowerCase().includes(q) ||
p.description?.toLowerCase().includes(q) ||
p.language.toLowerCase().includes(q),
);
}, [profiles, search]);
// Auto-select first profile if none selected
useEffect(() => {
if (!selectedVoiceId && profiles && profiles.length > 0) {
setSelectedVoiceId(profiles[0].id);
}
return counts;
}, [historyData]);
// Clear selection if selected profile was deleted
if (selectedVoiceId && profiles && !profiles.find((p) => p.id === selectedVoiceId)) {
setSelectedVoiceId(profiles.length > 0 ? profiles[0].id : null);
}
}, [profiles, selectedVoiceId, setSelectedVoiceId]);
// Get channel assignments for each profile
const { data: channelAssignments } = useQuery({
@@ -74,17 +83,6 @@ export function VoicesTab() {
queryFn: () => apiClient.listChannels(),
});
const handleEdit = (profileId: string) => {
setEditingProfileId(profileId);
setDialogOpen(true);
};
const handleDelete = (profileId: string) => {
if (confirm('Are you sure you want to delete this profile?')) {
deleteProfile.mutate(profileId);
}
};
const handleChannelChange = async (profileId: string, channelIds: string[]) => {
try {
await apiClient.setProfileChannels(profileId, channelIds);
@@ -103,56 +101,76 @@ export function VoicesTab() {
}
return (
<div className="h-full flex flex-col relative overflow-hidden">
{/* Scroll Mask - Always visible, behind content */}
<div className="absolute top-0 left-0 right-0 h-16 bg-gradient-to-b from-background to-transparent z-10 pointer-events-none" />
<div className="h-full flex gap-0 overflow-hidden -mx-8">
{/* Left: Table */}
<div className="flex-1 min-w-0 flex flex-col relative overflow-hidden">
{/* Scroll Mask */}
<div className="absolute top-0 left-0 right-0 h-16 bg-gradient-to-b from-background to-transparent z-10 pointer-events-none" />
{/* Fixed Header */}
<div className="absolute top-0 left-0 right-0 z-20">
<div className="flex items-center justify-between mb-6">
<h1 className="text-2xl font-bold">Voices</h1>
<Button onClick={() => setDialogOpen(true)}>
<Plus className="h-4 w-4 mr-2" />
New Voice
</Button>
{/* Fixed Header */}
<div className="absolute top-0 left-0 right-0 z-20 pl-8 pr-8">
<div className="flex items-center gap-3 mb-6">
<h1 className="text-2xl font-bold">Voices</h1>
<div className="flex-1" />
<div className="relative w-[240px]">
<Search className="absolute left-2.5 top-1/2 -translate-y-1/2 h-3.5 w-3.5 text-muted-foreground" />
<Input
placeholder="Search voices..."
value={search}
onChange={(e) => setSearch(e.target.value)}
className="h-10 pl-8 text-sm rounded-full focus-visible:ring-0 focus-visible:ring-offset-0"
/>
</div>
<Button onClick={() => setDialogOpen(true)}>
<Plus className="h-4 w-4 mr-2" />
New Voice
</Button>
</div>
</div>
{/* Scrollable Content */}
<div
ref={scrollRef}
className={cn(
'flex-1 overflow-y-auto overflow-x-hidden pt-16 relative z-0',
isPlayerVisible && BOTTOM_SAFE_AREA_PADDING,
)}
>
<Table className="table-fixed [&_td:first-child]:pl-8 [&_th:first-child]:pl-8">
<TableHeader>
<TableRow>
<TableHead className="w-[30%]">Name</TableHead>
<TableHead className="w-[10%]">Language</TableHead>
<TableHead className="w-[10%]">Generations</TableHead>
<TableHead className="w-[8%]">Samples</TableHead>
<TableHead className="w-[8%]">Effects</TableHead>
<TableHead className="w-[24%]">Channels</TableHead>
<TableHead className="w-6"></TableHead>
</TableRow>
</TableHeader>
<TableBody>
{filteredProfiles.map((profile) => (
<VoiceRow
key={profile.id}
profile={profile}
isSelected={selectedVoiceId === profile.id}
onSelect={() => setSelectedVoiceId(profile.id)}
channelIds={channelAssignments?.[profile.id] || []}
channels={channels || []}
onChannelChange={(channelIds) => handleChannelChange(profile.id, channelIds)}
/>
))}
</TableBody>
</Table>
</div>
</div>
{/* Scrollable Content */}
<div
ref={scrollRef}
className={cn(
'flex-1 overflow-y-auto pt-16 relative z-0',
isPlayerVisible && BOTTOM_SAFE_AREA_PADDING,
)}
>
<Table>
<TableHeader>
<TableRow>
<TableHead>Name</TableHead>
<TableHead>Language</TableHead>
<TableHead>Generations</TableHead>
<TableHead>Samples</TableHead>
<TableHead>Channels</TableHead>
<TableHead className="w-[50px]"></TableHead>
</TableRow>
</TableHeader>
<TableBody>
{profiles?.map((profile) => (
<VoiceRow
key={profile.id}
profile={profile}
generationCount={generationCounts[profile.id] || 0}
channelIds={channelAssignments?.[profile.id] || []}
channels={channels || []}
onChannelChange={(channelIds) => handleChannelChange(profile.id, channelIds)}
onEdit={() => handleEdit(profile.id)}
onDelete={() => handleDelete(profile.id)}
/>
))}
</TableBody>
</Table>
</div>
{/* Right: Inspector */}
{selectedVoiceId && (
<div className="w-[340px] shrink-0 border-l border-t rounded-tl-xl bg-muted/30">
<VoiceInspector key={selectedVoiceId} profileId={selectedVoiceId} />
</div>
)}
<ProfileForm />
</div>
@@ -161,43 +179,71 @@ export function VoicesTab() {
interface VoiceRowProps {
profile: VoiceProfileResponse;
generationCount: number;
isSelected: boolean;
onSelect: () => void;
channelIds: string[];
channels: Array<{ id: string; name: string; is_default: boolean }>;
onChannelChange: (channelIds: string[]) => void;
onEdit: () => void;
onDelete: () => void;
}
function VoiceRow({
profile,
generationCount,
isSelected,
onSelect,
channelIds,
channels,
onChannelChange,
onEdit,
onDelete,
}: VoiceRowProps) {
const { data: samples } = useProfileSamples(profile.id);
const serverUrl = useServerStore((state) => state.serverUrl);
const [avatarError, setAvatarError] = useState(false);
const avatarUrl = profile.avatar_path ? `${serverUrl}/profiles/${profile.id}/avatar` : null;
const enabledEffects = profile.effects_chain?.filter((e) => e.enabled) ?? [];
const effectsSummary = enabledEffects.map((e) => e.type).join(' → ');
return (
<TableRow className="cursor-pointer" onClick={onEdit}>
<TableRow
className={cn('cursor-pointer', isSelected ? 'bg-muted/50' : 'hover:bg-muted/50')}
onClick={onSelect}
>
<TableCell>
<div className="flex items-center gap-2">
<div className="h-8 w-8 rounded-lg bg-muted flex items-center justify-center shrink-0">
<Mic className="h-4 w-4 text-muted-foreground" />
<div className="flex w-full min-w-0 items-center gap-2">
<div className="h-8 w-8 rounded-full bg-muted flex items-center justify-center shrink-0 overflow-hidden">
{avatarUrl && !avatarError ? (
<img
src={avatarUrl}
alt={`${profile.name} avatar`}
className="h-full w-full object-cover"
onError={() => setAvatarError(true)}
/>
) : (
<Mic className="h-4 w-4 text-muted-foreground" />
)}
</div>
<div>
<div className="font-medium">{profile.name}</div>
<div className="min-w-0">
<div className="font-medium truncate">{profile.name}</div>
{profile.description && (
<div className="text-sm text-muted-foreground">{profile.description}</div>
<div className="text-sm text-muted-foreground truncate">{profile.description}</div>
)}
</div>
</div>
</TableCell>
<TableCell onClick={(e) => e.stopPropagation()}>{profile.language}</TableCell>
<TableCell onClick={(e) => e.stopPropagation()}>{generationCount}</TableCell>
<TableCell onClick={(e) => e.stopPropagation()}>{samples?.length || 0}</TableCell>
<TableCell>{profile.language}</TableCell>
<TableCell>{profile.generation_count}</TableCell>
<TableCell>{profile.sample_count}</TableCell>
<TableCell>
{enabledEffects.length > 0 ? (
<span
className="inline-flex items-center gap-1 text-xs text-accent"
title={effectsSummary}
>
<Sparkles className="h-3 w-3 fill-accent" />
{enabledEffects.length}
</span>
) : (
<span className="text-xs text-muted-foreground">—</span>
)}
</TableCell>
<TableCell onClick={(e) => e.stopPropagation()}>
<MultiSelect
options={channels.map((ch) => ({
@@ -207,28 +253,10 @@ function VoiceRow({
value={channelIds}
onChange={onChannelChange}
placeholder="Select channels..."
className="min-w-[200px]"
className="w-full"
/>
</TableCell>
<TableCell onClick={(e) => e.stopPropagation()}>
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button variant="ghost" size="icon">
<MoreHorizontal className="h-4 w-4" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent>
<DropdownMenuItem onClick={onEdit}>
<Edit className="h-4 w-4 mr-2" />
Edit
</DropdownMenuItem>
<DropdownMenuItem onClick={onDelete} className="text-destructive">
<Trash2 className="h-4 w-4 mr-2" />
Delete
</DropdownMenuItem>
</DropdownMenuContent>
</DropdownMenu>
</TableCell>
<TableCell />
</TableRow>
);
}
+1 -1
View File
@@ -111,4 +111,4 @@ export {
AlertDialogDescription,
AlertDialogAction,
AlertDialogCancel,
};
};
+1 -1
View File
@@ -1,5 +1,5 @@
import * as React from 'react';
import { Check } from 'lucide-react';
import * as React from 'react';
import { cn } from '@/lib/utils/cn';
export interface CheckboxProps {
+2 -1
View File
@@ -6,10 +6,11 @@ export interface CircleButtonProps extends React.ButtonHTMLAttributes<HTMLButton
}
const CircleButton = React.forwardRef<HTMLButtonElement, CircleButtonProps>(
({ className, icon: Icon, ...props }, ref) => {
({ className, icon: Icon, type = 'button', ...props }, ref) => {
return (
<button
ref={ref}
type={type}
className={cn(
'h-7 w-7 rounded-full flex items-center justify-center flex-shrink-0',
'hover:bg-muted transition-colors',
+5 -3
View File
@@ -1,6 +1,6 @@
import * as React from 'react';
import * as DropdownMenuPrimitive from '@radix-ui/react-dropdown-menu';
import { MoreHorizontal } from 'lucide-react';
import * as React from 'react';
import { cn } from '@/lib/utils/cn';
const DropdownMenu = DropdownMenuPrimitive.Root;
@@ -73,7 +73,7 @@ const DropdownMenuItem = React.forwardRef<
<DropdownMenuPrimitive.Item
ref={ref}
className={cn(
'relative flex cursor-default select-none items-center rounded-sm px-2 py-1.5 text-sm outline-none transition-colors focus:bg-accent focus:text-accent-foreground data-[disabled]:pointer-events-none data-[disabled]:opacity-50',
'relative flex cursor-default select-none items-center rounded-sm px-2 py-1.5 text-sm outline-none focus:bg-accent focus:text-accent-foreground data-[disabled]:pointer-events-none data-[disabled]:opacity-50',
inset && 'pl-8',
className,
)}
@@ -154,7 +154,9 @@ const DropdownMenuSeparator = React.forwardRef<
DropdownMenuSeparator.displayName = DropdownMenuPrimitive.Separator.displayName;
const DropdownMenuShortcut = ({ className, ...props }: React.HTMLAttributes<HTMLSpanElement>) => {
return <span className={cn('ml-auto text-xs tracking-widest opacity-60', className)} {...props} />;
return (
<span className={cn('ml-auto text-xs tracking-widest opacity-60', className)} {...props} />
);
};
DropdownMenuShortcut.displayName = 'DropdownMenuShortcut';
+2 -2
View File
@@ -16,7 +16,7 @@ const SelectTrigger = React.forwardRef<
<SelectPrimitive.Trigger
ref={ref}
className={cn(
'flex h-10 w-full items-center justify-between rounded-md border border-input bg-background px-3 py-2 text-sm ring-offset-background placeholder:text-muted-foreground focus:outline-none focus:ring-2 focus:ring-ring focus:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-50 [&>span]:line-clamp-1',
'flex h-10 w-full items-center justify-between rounded-md border border-input bg-background px-3 py-2 text-sm ring-offset-background placeholder:text-muted-foreground focus:outline-none focus:bg-muted/50 disabled:cursor-not-allowed disabled:opacity-50 [&>span]:line-clamp-1',
className,
)}
{...props}
@@ -108,7 +108,7 @@ const SelectItem = React.forwardRef<
<SelectPrimitive.Item
ref={ref}
className={cn(
'relative flex w-full cursor-default select-none items-center rounded-sm py-1.5 pl-8 pr-2 text-sm outline-none focus:bg-accent focus:text-accent-foreground data-[disabled]:pointer-events-none data-[disabled]:opacity-50',
'relative flex w-full cursor-default select-none items-center rounded-sm py-1.5 pl-8 pr-2 text-sm outline-none focus:bg-accent focus:text-accent-foreground focus:[&_*]:text-accent-foreground data-[disabled]:pointer-events-none data-[disabled]:opacity-50',
className,
)}
{...props}
+2 -2
View File
@@ -1,5 +1,5 @@
import * as React from 'react';
import * as SliderPrimitive from '@radix-ui/react-slider';
import * as React from 'react';
import { cn } from '@/lib/utils/cn';
const Slider = React.forwardRef<
@@ -14,7 +14,7 @@ const Slider = React.forwardRef<
<SliderPrimitive.Track className="relative h-2 w-full grow overflow-hidden rounded-full bg-secondary">
<SliderPrimitive.Range className="absolute h-full bg-primary" />
</SliderPrimitive.Track>
<SliderPrimitive.Thumb className="block h-5 w-5 rounded-full border-2 border-primary bg-background ring-offset-background transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:pointer-events-none disabled:opacity-50 translate-x-0.5" />
<SliderPrimitive.Thumb className="block h-0 w-0 outline-none disabled:pointer-events-none disabled:opacity-50 after:block after:h-5 after:w-5 after:rounded-full after:border-2 after:border-primary after:bg-background after:ring-offset-background after:transition-colors after:absolute after:top-1/2 after:left-1/2 after:-translate-x-1/2 after:-translate-y-1/2 focus-visible:after:ring-2 focus-visible:after:ring-ring focus-visible:after:ring-offset-2" />
</SliderPrimitive.Root>
));
Slider.displayName = SliderPrimitive.Root.displayName;
+6 -5
View File
@@ -14,7 +14,11 @@ const TableHeader = React.forwardRef<
HTMLTableSectionElement,
React.HTMLAttributes<HTMLTableSectionElement>
>(({ className, ...props }, ref) => (
<thead ref={ref} className={cn('[&_tr]:border-b', className)} {...props} />
<thead
ref={ref}
className={cn('[&_tr]:border-b [&_tr]:hover:bg-transparent', className)}
{...props}
/>
));
TableHeader.displayName = 'TableHeader';
@@ -42,10 +46,7 @@ const TableRow = React.forwardRef<HTMLTableRowElement, React.HTMLAttributes<HTML
({ className, ...props }, ref) => (
<tr
ref={ref}
className={cn(
'border-b transition-colors hover:bg-muted/50 data-[state=selected]:bg-muted',
className,
)}
className={cn('border-b hover:bg-muted/50 data-[state=selected]:bg-muted', className)}
{...props}
/>
),
+3 -1
View File
@@ -1,3 +1,4 @@
import { usePlayerStore } from '@/stores/playerStore';
import {
Toast,
ToastClose,
@@ -10,6 +11,7 @@ import { useToast } from './use-toast';
export function Toaster() {
const { toasts } = useToast();
const isPlayerOpen = !!usePlayerStore((s) => s.audioUrl);
return (
<ToastProvider>
@@ -23,7 +25,7 @@ export function Toaster() {
<ToastClose />
</Toast>
))}
<ToastViewport />
<ToastViewport className={isPlayerOpen ? 'sm:bottom-44' : ''} />
</ToastProvider>
);
}
+48
View File
@@ -0,0 +1,48 @@
import * as React from 'react';
import { cn } from '@/lib/utils/cn';
export interface ToggleProps {
checked?: boolean;
onCheckedChange?: (checked: boolean) => void;
disabled?: boolean;
className?: string;
id?: string;
}
const Toggle = React.forwardRef<HTMLButtonElement, ToggleProps>(
({ checked = false, onCheckedChange, disabled = false, className, id, ...props }, ref) => {
return (
<button
type="button"
ref={ref}
id={id}
role="switch"
aria-checked={checked}
disabled={disabled}
onClick={() => {
if (!disabled && onCheckedChange) {
onCheckedChange(!checked);
}
}}
className={cn(
'relative inline-flex h-5 w-9 shrink-0 items-center rounded-full transition-colors',
'focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2',
checked ? 'bg-accent' : 'bg-muted-foreground/25',
disabled ? 'opacity-50 cursor-not-allowed' : 'cursor-pointer',
className,
)}
{...props}
>
<span
className={cn(
'pointer-events-none block h-4 w-4 rounded-full bg-white shadow-sm transition-transform',
checked ? 'translate-x-[18px]' : 'translate-x-[2px]',
)}
/>
</button>
);
},
);
Toggle.displayName = 'Toggle';
export { Toggle };
+5
View File
@@ -1,3 +1,8 @@
interface Window {
__voiceboxServerStartedByApp?: boolean;
}
declare module 'virtual:changelog' {
const raw: string;
export default raw;
}
+13 -4
View File
@@ -5,7 +5,15 @@ import type { UpdateStatus } from '@/platform/types';
// Re-export UpdateStatus for backwards compatibility
export type { UpdateStatus };
export function useAutoUpdater(checkOnMount = false) {
interface UseAutoUpdaterOptions {
checkOnMount?: boolean;
showToast?: boolean;
}
export function useAutoUpdater(options: boolean | UseAutoUpdaterOptions = false) {
const { checkOnMount } =
typeof options === 'boolean' ? { checkOnMount: options } : { checkOnMount: options.checkOnMount ?? false };
const platform = usePlatform();
const [status, setStatus] = useState<UpdateStatus>(platform.updater.getStatus());
const hasCheckedRef = useRef(false);
@@ -38,10 +46,11 @@ export function useAutoUpdater(checkOnMount = false) {
useEffect(() => {
if (checkOnMount && platform.metadata.isTauri && !hasCheckedRef.current) {
hasCheckedRef.current = true;
checkForUpdates();
checkForUpdates().catch((error) => {
console.error('Auto update check failed:', error);
});
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [platform.metadata.isTauricheckOnMountcheckForUpdates]);
}, [checkOnMount, checkForUpdates, platform.metadata.isTauri]);
return {
status,
+1 -1
View File
@@ -73,7 +73,7 @@ export function useAutoUpdater(options: boolean | UseAutoUpdaterOptions = false)
}
// Empty dependency array - only run once on mount
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [platform.metadata.isTauricheckOnMountcheckForUpdates]);
}, [checkOnMount, checkForUpdates, platform.metadata.isTauri]);
// Show toast when update is available
useEffect(() => {
+16
View File
@@ -1,4 +1,5 @@
@import "tailwindcss" source(".");
@import "loaders.css/loaders.min.css";
@theme {
--radius-sm: calc(var(--radius) - 4px);
@@ -155,3 +156,18 @@
animation: fadeIn 0.5s ease-out 0.15s forwards;
opacity: 0;
}
/* react-loaders */
.line-scale-pulse-out-rapid > div,
.line-scale > div {
background-color: hsl(var(--accent)) !important;
}
.loader-hidden {
display: block;
}
.loader-hidden > div > div {
animation-play-state: paused !important;
background-color: hsl(var(--muted-foreground)) !important;
}
+286 -42
View File
@@ -1,31 +1,56 @@
import { useServerStore } from '@/stores/serverStore';
import type { LanguageCode } from '@/lib/constants/languages';
import { useServerStore } from '@/stores/serverStore';
import type {
VoiceProfileCreate,
VoiceProfileResponse,
ProfileSampleResponse,
ActiveTasksResponse,
ApplyEffectsRequest,
AvailableEffectsResponse,
CudaStatus,
EffectConfig,
EffectPresetCreate,
EffectPresetResponse,
GenerationRequest,
GenerationResponse,
HistoryQuery,
HistoryListResponse,
HistoryResponse,
TranscriptionResponse,
GenerationVersionResponse,
HealthResponse,
ModelStatusListResponse,
HistoryListResponse,
HistoryQuery,
HistoryResponse,
ModelDownloadRequest,
ActiveTasksResponse,
ModelStatusListResponse,
PresetVoice,
ProfileSampleResponse,
StoryCreate,
StoryResponse,
StoryDetailResponse,
StoryItemBatchUpdate,
StoryItemCreate,
StoryItemDetail,
StoryItemBatchUpdate,
StoryItemReorder,
StoryItemMove,
StoryItemTrim,
StoryItemReorder,
StoryItemSplit,
StoryItemTrim,
StoryItemVersionUpdate,
StoryResponse,
TranscriptionResponse,
VoiceProfileCreate,
VoiceProfileResponse,
WhisperModelSize,
} from './types';
function formatErrorDetail(detail: unknown, fallback: string): string {
if (typeof detail === 'string') return detail;
if (Array.isArray(detail)) {
return detail
.map((e: Record<string, unknown>) => e.msg || e.message || JSON.stringify(e))
.join('; ');
}
if (detail && typeof detail === 'object') {
const obj = detail as Record<string, unknown>;
if (typeof obj.message === 'string') return obj.message;
return JSON.stringify(detail);
}
return fallback;
}
class ApiClient {
private getBaseUrl(): string {
const serverUrl = useServerStore.getState().serverUrl;
@@ -46,7 +71,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.json();
@@ -73,6 +98,10 @@ class ApiClient {
return this.request<VoiceProfileResponse>(`/profiles/${profileId}`);
}
async listPresetVoices(engine: string): Promise<{ engine: string; voices: PresetVoice[] }> {
return this.request<{ engine: string; voices: PresetVoice[] }>(`/profiles/presets/${engine}`);
}
async updateProfile(profileId: string, data: VoiceProfileCreate): Promise<VoiceProfileResponse> {
return this.request<VoiceProfileResponse>(`/profiles/${profileId}`, {
method: 'PUT',
@@ -105,7 +134,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.json();
@@ -139,7 +168,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.blob();
@@ -159,7 +188,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.json();
@@ -179,7 +208,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.json();
@@ -199,6 +228,30 @@ class ApiClient {
});
}
async retryGeneration(generationId: string): Promise<GenerationResponse> {
return this.request<GenerationResponse>(`/generate/${generationId}/retry`, {
method: 'POST',
});
}
async cancelGeneration(generationId: string): Promise<{ message: string }> {
return this.request<{ message: string }>(`/generate/${generationId}/cancel`, {
method: 'POST',
});
}
async regenerateGeneration(generationId: string): Promise<GenerationResponse> {
return this.request<GenerationResponse>(`/generate/${generationId}/regenerate`, {
method: 'POST',
});
}
async toggleFavorite(generationId: string): Promise<{ is_favorited: boolean }> {
return this.request<{ is_favorited: boolean }>(`/history/${generationId}/favorite`, {
method: 'POST',
});
}
// History
async listHistory(query?: HistoryQuery): Promise<HistoryListResponse> {
const params = new URLSearchParams();
@@ -223,6 +276,12 @@ class ApiClient {
});
}
async clearFailedGenerations(): Promise<{ deleted: number }> {
return this.request<{ deleted: number }>(`/history/failed`, {
method: 'DELETE',
});
}
async exportGeneration(generationId: string): Promise<Blob> {
const url = `${this.getBaseUrl()}/history/${generationId}/export`;
const response = await fetch(url);
@@ -231,7 +290,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.blob();
@@ -245,13 +304,19 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.blob();
}
async importGeneration(file: File): Promise<{ id: string; profile_id: string; profile_name: string; text: string; message: string }> {
async importGeneration(file: File): Promise<{
id: string;
profile_id: string;
profile_name: string;
text: string;
message: string;
}> {
const url = `${this.getBaseUrl()}/history/import`;
const formData = new FormData();
formData.append('file', file);
@@ -265,12 +330,17 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.json();
}
// Generation status SSE
getGenerationStatusUrl(generationId: string): string {
return `${this.getBaseUrl()}/generate/${generationId}/status`;
}
// Audio
getAudioUrl(audioId: string): string {
return `${this.getBaseUrl()}/audio/${audioId}`;
@@ -281,12 +351,19 @@ class ApiClient {
}
// Transcription
async transcribeAudio(file: File, language?: LanguageCode): Promise<TranscriptionResponse> {
async transcribeAudio(
file: File,
language?: LanguageCode,
model?: WhisperModelSize,
): Promise<TranscriptionResponse> {
const formData = new FormData();
formData.append('file', file);
if (language) {
formData.append('language', language);
}
if (model) {
formData.append('model', model);
}
const url = `${this.getBaseUrl()}/transcribe`;
const response = await fetch(url, {
@@ -298,7 +375,7 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.json();
@@ -309,8 +386,30 @@ class ApiClient {
return this.request<ModelStatusListResponse>('/models/status');
}
async getModelsCacheDir(): Promise<{ path: string }> {
return this.request<{ path: string }>('/models/cache-dir');
}
async migrateModels(
destination: string,
): Promise<{ source: string; destination: string; moved: number; errors: string[] }> {
return this.request('/models/migrate', {
method: 'POST',
body: JSON.stringify({ destination }),
});
}
getMigrationProgressUrl(): string {
return `${this.getBaseUrl()}/models/migrate/progress`;
}
async triggerModelDownload(modelName: string): Promise<{ message: string }> {
console.log('[API] triggerModelDownload called for:', modelName, 'at', new Date().toISOString());
console.log(
'[API] triggerModelDownload called for:',
modelName,
'at',
new Date().toISOString(),
);
const result = await this.request<{ message: string }>('/models/download', {
method: 'POST',
body: JSON.stringify({ model_name: modelName } as ModelDownloadRequest),
@@ -325,11 +424,28 @@ class ApiClient {
});
}
async unloadModel(modelName: string): Promise<{ message: string }> {
return this.request<{ message: string }>(`/models/${modelName}/unload`, {
method: 'POST',
});
}
async cancelDownload(modelName: string): Promise<{ message: string }> {
return this.request<{ message: string }>('/models/download/cancel', {
method: 'POST',
body: JSON.stringify({ model_name: modelName } as ModelDownloadRequest),
});
}
// Task Management
async getActiveTasks(): Promise<ActiveTasksResponse> {
return this.request<ActiveTasksResponse>('/tasks/active');
}
async clearAllTasks(): Promise<{ message: string }> {
return this.request<{ message: string }>('/tasks/clear', { method: 'POST' });
}
// Audio Channels
async listChannels(): Promise<
Array<{
@@ -343,10 +459,7 @@ class ApiClient {
return this.request('/channels');
}
async createChannel(data: {
name: string;
device_ids: string[];
}): Promise<{
async createChannel(data: { name: string; device_ids: string[] }): Promise<{
id: string;
name: string;
is_default: boolean;
@@ -388,10 +501,7 @@ class ApiClient {
return this.request(`/channels/${channelId}/voices`);
}
async setChannelVoices(
channelId: string,
profileIds: string[],
): Promise<{ message: string }> {
async setChannelVoices(channelId: string, profileIds: string[]): Promise<{ message: string }> {
return this.request(`/channels/${channelId}/voices`, {
method: 'PUT',
body: JSON.stringify({ profile_ids: profileIds }),
@@ -402,16 +512,30 @@ class ApiClient {
return this.request(`/profiles/${profileId}/channels`);
}
async setProfileChannels(
profileId: string,
channelIds: string[],
): Promise<{ message: string }> {
async setProfileChannels(profileId: string, channelIds: string[]): Promise<{ message: string }> {
return this.request(`/profiles/${profileId}/channels`, {
method: 'PUT',
body: JSON.stringify({ channel_ids: channelIds }),
});
}
// CUDA Backend Management
async getCudaStatus(): Promise<CudaStatus> {
return this.request<CudaStatus>('/backend/cuda-status');
}
async downloadCudaBackend(): Promise<{ message: string; progress_key: string }> {
return this.request<{ message: string; progress_key: string }>('/backend/download-cuda', {
method: 'POST',
});
}
async deleteCudaBackend(): Promise<{ message: string }> {
return this.request<{ message: string }>('/backend/cuda', {
method: 'DELETE',
});
}
// Stories
async listStories(): Promise<StoryResponse[]> {
return this.request<StoryResponse[]>('/stories');
@@ -468,21 +592,33 @@ class ApiClient {
});
}
async moveStoryItem(storyId: string, itemId: string, data: StoryItemMove): Promise<StoryItemDetail> {
async moveStoryItem(
storyId: string,
itemId: string,
data: StoryItemMove,
): Promise<StoryItemDetail> {
return this.request<StoryItemDetail>(`/stories/${storyId}/items/${itemId}/move`, {
method: 'PUT',
body: JSON.stringify(data),
});
}
async trimStoryItem(storyId: string, itemId: string, data: StoryItemTrim): Promise<StoryItemDetail> {
async trimStoryItem(
storyId: string,
itemId: string,
data: StoryItemTrim,
): Promise<StoryItemDetail> {
return this.request<StoryItemDetail>(`/stories/${storyId}/items/${itemId}/trim`, {
method: 'PUT',
body: JSON.stringify(data),
});
}
async splitStoryItem(storyId: string, itemId: string, data: StoryItemSplit): Promise<StoryItemDetail[]> {
async splitStoryItem(
storyId: string,
itemId: string,
data: StoryItemSplit,
): Promise<StoryItemDetail[]> {
return this.request<StoryItemDetail[]>(`/stories/${storyId}/items/${itemId}/split`, {
method: 'POST',
body: JSON.stringify(data),
@@ -495,6 +631,17 @@ class ApiClient {
});
}
async setStoryItemVersion(
storyId: string,
itemId: string,
data: StoryItemVersionUpdate,
): Promise<StoryItemDetail> {
return this.request<StoryItemDetail>(`/stories/${storyId}/items/${itemId}/version`, {
method: 'PUT',
body: JSON.stringify(data),
});
}
async exportStoryAudio(storyId: string): Promise<Blob> {
const url = `${this.getBaseUrl()}/stories/${storyId}/export-audio`;
const response = await fetch(url);
@@ -503,7 +650,104 @@ class ApiClient {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(error.detail || `HTTP error! status: ${response.status}`);
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.blob();
}
// Effects & Versions
async getAvailableEffects(): Promise<AvailableEffectsResponse> {
return this.request<AvailableEffectsResponse>('/effects/available');
}
async listEffectPresets(): Promise<EffectPresetResponse[]> {
return this.request<EffectPresetResponse[]>('/effects/presets');
}
async createEffectPreset(data: EffectPresetCreate): Promise<EffectPresetResponse> {
return this.request<EffectPresetResponse>('/effects/presets', {
method: 'POST',
body: JSON.stringify(data),
});
}
async updateEffectPreset(
presetId: string,
data: { name?: string; description?: string; effects_chain?: EffectConfig[] },
): Promise<EffectPresetResponse> {
return this.request<EffectPresetResponse>(`/effects/presets/${presetId}`, {
method: 'PUT',
body: JSON.stringify(data),
});
}
async deleteEffectPreset(presetId: string): Promise<void> {
await this.request<void>(`/effects/presets/${presetId}`, {
method: 'DELETE',
});
}
async listGenerationVersions(generationId: string): Promise<GenerationVersionResponse[]> {
return this.request<GenerationVersionResponse[]>(`/generations/${generationId}/versions`);
}
async applyEffectsToGeneration(
generationId: string,
data: ApplyEffectsRequest,
): Promise<GenerationVersionResponse> {
return this.request<GenerationVersionResponse>(
`/generations/${generationId}/versions/apply-effects`,
{
method: 'POST',
body: JSON.stringify(data),
},
);
}
async setDefaultVersion(
generationId: string,
versionId: string,
): Promise<GenerationVersionResponse> {
return this.request<GenerationVersionResponse>(
`/generations/${generationId}/versions/${versionId}/set-default`,
{ method: 'PUT' },
);
}
async deleteGenerationVersion(generationId: string, versionId: string): Promise<void> {
await this.request<void>(`/generations/${generationId}/versions/${versionId}`, {
method: 'DELETE',
});
}
getVersionAudioUrl(versionId: string): string {
return `${this.getBaseUrl()}/audio/version/${versionId}`;
}
async updateProfileEffects(
profileId: string,
effectsChain: EffectConfig[] | null,
): Promise<VoiceProfileResponse> {
return this.request<VoiceProfileResponse>(`/profiles/${profileId}/effects`, {
method: 'PUT',
body: JSON.stringify({ effects_chain: effectsChain }),
});
}
async previewEffects(generationId: string, effectsChain: EffectConfig[]): Promise<Blob> {
const url = `${this.getBaseUrl()}/effects/preview/${generationId}`;
const response = await fetch(url, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ effects_chain: effectsChain }),
});
if (!response.ok) {
const error = await response.json().catch(() => ({
detail: response.statusText,
}));
throw new Error(formatErrorDetail(error.detail, `HTTP error! status: ${response.status}`));
}
return response.blob();
+169 -4
View File
@@ -1,10 +1,17 @@
// API Types matching backend Pydantic models
import type { LanguageCode } from '@/lib/constants/languages';
export type VoiceType = 'cloned' | 'preset' | 'designed';
export interface VoiceProfileCreate {
name: string;
description?: string;
language: LanguageCode;
voice_type?: VoiceType;
preset_engine?: string;
preset_voice_id?: string;
design_prompt?: string;
default_engine?: string;
}
export interface VoiceProfileResponse {
@@ -13,10 +20,25 @@ export interface VoiceProfileResponse {
description?: string;
language: string;
avatar_path?: string;
effects_chain?: EffectConfig[];
voice_type: VoiceType;
preset_engine?: string;
preset_voice_id?: string;
design_prompt?: string;
default_engine?: string;
generation_count: number;
sample_count: number;
created_at: string;
updated_at: string;
}
export interface PresetVoice {
voice_id: string;
name: string;
gender: 'male' | 'female';
language: string;
}
export interface ProfileSampleCreate {
reference_text: string;
}
@@ -28,12 +50,42 @@ export interface ProfileSampleResponse {
reference_text: string;
}
export interface EffectConfig {
type: string;
enabled: boolean;
params: Record<string, number>;
}
export interface GenerationRequest {
profile_id: string;
text: string;
language: LanguageCode;
seed?: number;
model_size?: '1.7B' | '0.6B';
model_size?: '1.7B' | '0.6B' | '1B' | '3B';
engine?:
| 'qwen'
| 'qwen_custom_voice'
| 'luxtts'
| 'chatterbox'
| 'chatterbox_turbo'
| 'tada'
| 'kokoro';
instruct?: string;
max_chunk_chars?: number;
crossfade_ms?: number;
normalize?: boolean;
effects_chain?: EffectConfig[];
}
export interface GenerationVersionResponse {
id: string;
generation_id: string;
label: string;
audio_path: string;
effects_chain?: EffectConfig[];
source_version_id?: string;
is_default: boolean;
created_at: string;
}
export interface GenerationResponse {
@@ -41,10 +93,18 @@ export interface GenerationResponse {
profile_id: string;
text: string;
language: string;
audio_path: string;
duration: number;
audio_path?: string;
duration?: number;
seed?: number;
instruct?: string;
engine?: string;
model_size?: string;
status: 'loading_model' | 'generating' | 'completed' | 'failed';
error?: string;
is_favorited?: boolean;
created_at: string;
versions?: GenerationVersionResponse[];
active_version_id?: string;
}
export interface HistoryQuery {
@@ -56,6 +116,8 @@ export interface HistoryQuery {
export interface HistoryResponse extends GenerationResponse {
profile_name: string;
versions?: GenerationVersionResponse[];
active_version_id?: string;
}
export interface HistoryListResponse {
@@ -63,8 +125,11 @@ export interface HistoryListResponse {
total: number;
}
export type WhisperModelSize = 'base' | 'small' | 'medium' | 'large' | 'turbo';
export interface TranscriptionRequest {
language?: LanguageCode;
model?: WhisperModelSize;
}
export interface TranscriptionResponse {
@@ -78,7 +143,29 @@ export interface HealthResponse {
model_downloaded?: boolean;
model_size?: string;
gpu_available: boolean;
gpu_type?: string;
vram_used_mb?: number;
backend_type?: string;
backend_variant?: string; // "cpu" or "cuda"
}
export interface CudaDownloadProgress {
model_name: string;
current: number;
total: number;
progress: number;
filename?: string;
status: 'downloading' | 'extracting' | 'complete' | 'error';
timestamp: string;
error?: string;
}
export interface CudaStatus {
available: boolean; // CUDA binary exists on disk
active: boolean; // Currently running the CUDA binary
binary_path?: string;
downloading: boolean; // Download in progress
download_progress?: CudaDownloadProgress;
}
export interface ModelProgress {
@@ -95,12 +182,29 @@ export interface ModelProgress {
export interface ModelStatus {
model_name: string;
display_name: string;
hf_repo_id?: string; // HuggingFace repository ID
downloaded: boolean;
downloading: boolean; // True if download is in progress
downloading: boolean; // True if download is in progress
size_mb?: number;
loaded: boolean;
}
export interface HuggingFaceModelInfo {
id: string;
author: string;
lastModified: string;
pipeline_tag?: string;
library_name?: string;
downloads: number;
likes: number;
tags: string[];
cardData?: {
license?: string;
language?: string[];
pipeline_tag?: string;
};
}
export interface ModelStatusListResponse {
models: ModelStatus[];
}
@@ -113,6 +217,11 @@ export interface ActiveDownloadTask {
model_name: string;
status: string;
started_at: string;
error?: string;
progress?: number; // 0-100 percentage
current?: number; // bytes downloaded
total?: number; // total bytes
filename?: string; // current file being downloaded
}
export interface ActiveGenerationTask {
@@ -145,6 +254,7 @@ export interface StoryItemDetail {
id: string;
story_id: string;
generation_id: string;
version_id?: string;
start_time_ms: number;
track: number;
trim_start_ms: number;
@@ -159,6 +269,12 @@ export interface StoryItemDetail {
seed?: number;
instruct?: string;
generation_created_at: string;
versions?: GenerationVersionResponse[];
active_version_id?: string;
}
export interface StoryItemVersionUpdate {
version_id: string | null;
}
export interface StoryDetailResponse {
@@ -202,3 +318,52 @@ export interface StoryItemTrim {
export interface StoryItemSplit {
split_time_ms: number;
}
// Effects
export interface EffectPresetResponse {
id: string;
name: string;
description?: string;
effects_chain: EffectConfig[];
is_builtin: boolean;
created_at: string;
}
export interface EffectPresetCreate {
name: string;
description?: string;
effects_chain: EffectConfig[];
}
export interface EffectPresetUpdate {
name?: string;
description?: string;
effects_chain?: EffectConfig[];
}
export interface AvailableEffectParam {
default: number;
min: number;
max: number;
step: number;
description: string;
}
export interface AvailableEffect {
type: string;
label: string;
description: string;
params: Record<string, AvailableEffectParam>;
}
export interface AvailableEffectsResponse {
effects: AvailableEffect[];
}
export interface ApplyEffectsRequest {
effects_chain: EffectConfig[];
source_version_id?: string;
label?: string;
set_as_default?: boolean;
}
+76 -12
View File
@@ -1,26 +1,90 @@
/**
* Supported languages for Qwen3-TTS
* Based on: https://github.com/QwenLM/Qwen3-TTS
* Supported languages for voice generation, per engine.
*
* Qwen3-TTS supports 10 languages.
* LuxTTS is English-only.
* Chatterbox Multilingual supports 23 languages.
* Chatterbox Turbo is English-only.
* Kokoro supports 8 languages.
*/
export const SUPPORTED_LANGUAGES = {
zh: 'Chinese',
/** All languages that any engine supports. */
export const ALL_LANGUAGES = {
ar: 'Arabic',
da: 'Danish',
de: 'German',
el: 'Greek',
en: 'English',
es: 'Spanish',
fi: 'Finnish',
fr: 'French',
he: 'Hebrew',
hi: 'Hindi',
it: 'Italian',
ja: 'Japanese',
ko: 'Korean',
de: 'German',
fr: 'French',
ru: 'Russian',
ms: 'Malay',
nl: 'Dutch',
no: 'Norwegian',
pl: 'Polish',
pt: 'Portuguese',
es: 'Spanish',
it: 'Italian',
ru: 'Russian',
sv: 'Swedish',
sw: 'Swahili',
tr: 'Turkish',
zh: 'Chinese',
} as const;
export type LanguageCode = keyof typeof SUPPORTED_LANGUAGES;
export type LanguageCode = keyof typeof ALL_LANGUAGES;
export const LANGUAGE_CODES = Object.keys(SUPPORTED_LANGUAGES) as LanguageCode[];
/** Per-engine supported language codes. */
export const ENGINE_LANGUAGES: Record<string, readonly LanguageCode[]> = {
qwen: ['zh', 'en', 'ja', 'ko', 'de', 'fr', 'ru', 'pt', 'es', 'it'],
luxtts: ['en'],
chatterbox: [
'ar',
'da',
'de',
'el',
'en',
'es',
'fi',
'fr',
'he',
'hi',
'it',
'ja',
'ko',
'ms',
'nl',
'no',
'pl',
'pt',
'ru',
'sv',
'sw',
'tr',
'zh',
],
chatterbox_turbo: ['en'],
tada: ['en', 'ar', 'zh', 'de', 'es', 'fr', 'it', 'ja', 'pl', 'pt'],
kokoro: ['en', 'es', 'fr', 'hi', 'it', 'pt', 'ja', 'zh'],
qwen_custom_voice: ['zh', 'en', 'ja', 'ko', 'de', 'fr', 'ru', 'pt', 'es', 'it'],
} as const;
/** Helper: get language options for a given engine. */
export function getLanguageOptionsForEngine(engine: string) {
const codes = ENGINE_LANGUAGES[engine] ?? ENGINE_LANGUAGES.qwen;
return codes.map((code) => ({
value: code,
label: ALL_LANGUAGES[code],
}));
}
// ── Backwards-compatible exports used elsewhere ──────────────────────
export const SUPPORTED_LANGUAGES = ALL_LANGUAGES;
export const LANGUAGE_CODES = Object.keys(ALL_LANGUAGES) as LanguageCode[];
export const LANGUAGE_OPTIONS = LANGUAGE_CODES.map((code) => ({
value: code,
label: SUPPORTED_LANGUAGES[code],
label: ALL_LANGUAGES[code],
}));
+5 -2
View File
@@ -2,11 +2,14 @@
* UI layout constants for safe area padding
*/
const isWindows = typeof navigator !== 'undefined' && navigator.userAgent.includes('Windows');
/**
* Top safe area padding - height of the drag region bar
* Corresponds to Tailwind's pt-12 (3rem / 48px)
* On macOS this accounts for the overlay titlebar (48px).
* On Windows the native title bar is outside the webview, so no padding is needed.
*/
export const TOP_SAFE_AREA_PADDING = 'pt-12';
export const TOP_SAFE_AREA_PADDING = isWindows ? 'pt-8' : 'pt-12';
/**
* Bottom safe area padding - height of the audio player
+26 -20
View File
@@ -20,11 +20,13 @@ export function useAudioRecording({
const streamRef = useRef<MediaStream | null>(null);
const timerRef = useRef<number | null>(null);
const startTimeRef = useRef<number | null>(null);
const cancelledRef = useRef<boolean>(false);
const startRecording = useCallback(async () => {
try {
setError(null);
chunksRef.current = [];
cancelledRef.current = false;
setDuration(0);
// Check if getUserMedia is available
@@ -87,31 +89,34 @@ export function useAudioRecording({
};
mediaRecorder.onstop = async () => {
// Snapshot the cancellation flag and recorded duration immediately —
// cancelRecording() clears chunks and sets cancelledRef synchronously
// before this async handler runs, so we must check it first.
const wasCancelled = cancelledRef.current;
const recordedDuration = startTimeRef.current
? (Date.now() - startTimeRef.current) / 1000
: undefined;
const webmBlob = new Blob(chunksRef.current, { type: 'audio/webm' });
// Convert to WAV format to avoid needing ffmpeg on backend
try {
const wavBlob = await convertToWav(webmBlob);
// Pass the actual recorded duration
const recordedDuration = startTimeRef.current
? (Date.now() - startTimeRef.current) / 1000
: undefined;
onRecordingComplete?.(wavBlob, recordedDuration);
} catch (err) {
console.error('Error converting audio to WAV:', err);
// Fallback to original blob if conversion fails
const recordedDuration = startTimeRef.current
? (Date.now() - startTimeRef.current) / 1000
: undefined;
onRecordingComplete?.(webmBlob, recordedDuration);
}
// Stop all tracks
// Stop all tracks now that we have the data
streamRef.current?.getTracks().forEach((track) => {
track.stop();
});
streamRef.current = null;
// Don't fire completion callback if the recording was cancelled
if (wasCancelled) return;
// Convert to WAV format to avoid needing ffmpeg on backend
try {
const wavBlob = await convertToWav(webmBlob);
onRecordingComplete?.(wavBlob, recordedDuration);
} catch (err) {
console.error('Error converting audio to WAV:', err);
// Fallback to original blob if conversion fails
onRecordingComplete?.(webmBlob, recordedDuration);
}
};
mediaRecorder.onerror = (event) => {
@@ -167,9 +172,10 @@ export function useAudioRecording({
const cancelRecording = useCallback(() => {
if (mediaRecorderRef.current) {
cancelledRef.current = true; // Must be set before stop() triggers onstop
chunksRef.current = [];
mediaRecorderRef.current.stop();
setIsRecording(false);
chunksRef.current = [];
setDuration(0);
}
+86 -20
View File
@@ -4,18 +4,31 @@ import { useForm } from 'react-hook-form';
import * as z from 'zod';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import type { EffectConfig } from '@/lib/api/types';
import { LANGUAGE_CODES, type LanguageCode } from '@/lib/constants/languages';
import { useGeneration } from '@/lib/hooks/useGeneration';
import { useModelDownloadToast } from '@/lib/hooks/useModelDownloadToast';
import { useGenerationStore } from '@/stores/generationStore';
import { usePlayerStore } from '@/stores/playerStore';
import { useServerStore } from '@/stores/serverStore';
import { useUIStore } from '@/stores/uiStore';
const generationSchema = z.object({
text: z.string().min(1, 'Text is required').max(5000),
text: z.string().min(1, '').max(50000),
language: z.enum(LANGUAGE_CODES as [LanguageCode, ...LanguageCode[]]),
seed: z.number().int().optional(),
modelSize: z.enum(['1.7B', '0.6B']).optional(),
modelSize: z.enum(['1.7B', '0.6B', '1B', '3B']).optional(),
instruct: z.string().max(500).optional(),
engine: z
.enum([
'qwen',
'qwen_custom_voice',
'luxtts',
'chatterbox',
'chatterbox_turbo',
'tada',
'kokoro',
])
.optional(),
});
export type GenerationFormValues = z.infer<typeof generationSchema>;
@@ -23,13 +36,17 @@ export type GenerationFormValues = z.infer<typeof generationSchema>;
interface UseGenerationFormOptions {
onSuccess?: (generationId: string) => void;
defaultValues?: Partial<GenerationFormValues>;
getEffectsChain?: () => EffectConfig[] | undefined;
}
export function useGenerationForm(options: UseGenerationFormOptions = {}) {
const { toast } = useToast();
const generation = useGeneration();
const setAudioWithAutoPlay = usePlayerStore((state) => state.setAudioWithAutoPlay);
const setIsGenerating = useGenerationStore((state) => state.setIsGenerating);
const addPendingGeneration = useGenerationStore((state) => state.addPendingGeneration);
const maxChunkChars = useServerStore((state) => state.maxChunkChars);
const crossfadeMs = useServerStore((state) => state.crossfadeMs);
const normalizeAudio = useServerStore((state) => state.normalizeAudio);
const selectedEngine = useUIStore((state) => state.selectedEngine);
const [downloadingModelName, setDownloadingModelName] = useState<string | null>(null);
const [downloadingDisplayName, setDownloadingDisplayName] = useState<string | null>(null);
@@ -47,6 +64,7 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
seed: undefined,
modelSize: '1.7B',
instruct: '',
engine: (selectedEngine as GenerationFormValues['engine']) || 'qwen',
...options.defaultValues,
},
});
@@ -65,11 +83,45 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
}
try {
setIsGenerating(true);
const modelName = `qwen-tts-${data.modelSize}`;
const displayName = data.modelSize === '1.7B' ? 'Qwen TTS 1.7B' : 'Qwen TTS 0.6B';
const engine = data.engine || 'qwen';
const modelName =
engine === 'luxtts'
? 'luxtts'
: engine === 'chatterbox'
? 'chatterbox-tts'
: engine === 'chatterbox_turbo'
? 'chatterbox-turbo'
: engine === 'tada'
? data.modelSize === '3B'
? 'tada-3b-ml'
: 'tada-1b'
: engine === 'kokoro'
? 'kokoro'
: engine === 'qwen_custom_voice'
? `qwen-custom-voice-${data.modelSize}`
: `qwen-tts-${data.modelSize}`;
const displayName =
engine === 'luxtts'
? 'LuxTTS'
: engine === 'chatterbox'
? 'Chatterbox TTS'
: engine === 'chatterbox_turbo'
? 'Chatterbox Turbo'
: engine === 'tada'
? data.modelSize === '3B'
? 'TADA 3B Multilingual'
: 'TADA 1B'
: engine === 'kokoro'
? 'Kokoro 82M'
: engine === 'qwen_custom_voice'
? data.modelSize === '1.7B'
? 'Qwen CustomVoice 1.7B'
: 'Qwen CustomVoice 0.6B'
: data.modelSize === '1.7B'
? 'Qwen TTS 1.7B'
: 'Qwen TTS 0.6B';
// Check if model needs downloading
try {
const modelStatus = await apiClient.getModelStatus();
const model = modelStatus.models.find((m) => m.model_name === modelName);
@@ -82,24 +134,39 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
console.error('Failed to check model status:', error);
}
const hasModelSizes =
engine === 'qwen' || engine === 'qwen_custom_voice' || engine === 'tada';
// Only Qwen CustomVoice actually honors the instruct kwarg at model level.
// Base Qwen3-TTS accepts the kwarg but ignores it.
const supportsInstruct = engine === 'qwen_custom_voice';
const effectsChain = options.getEffectsChain?.();
// This now returns immediately with status="generating"
const result = await generation.mutateAsync({
profile_id: selectedProfileId,
text: data.text,
language: data.language,
seed: data.seed,
model_size: data.modelSize,
instruct: data.instruct || undefined,
model_size: hasModelSizes ? data.modelSize : undefined,
engine,
instruct: supportsInstruct ? data.instruct || undefined : undefined,
max_chunk_chars: maxChunkChars,
crossfade_ms: crossfadeMs,
normalize: normalizeAudio,
effects_chain: effectsChain?.length ? effectsChain : undefined,
});
toast({
title: 'Generation complete!',
description: `Audio generated (${result.duration.toFixed(2)}s)`,
// Track this generation for SSE status updates
addPendingGeneration(result.id);
// Reset form immediately — user can start typing again
form.reset({
text: '',
language: data.language,
seed: undefined,
modelSize: data.modelSize,
instruct: '',
engine: data.engine,
});
const audioUrl = apiClient.getAudioUrl(result.id);
setAudioWithAutoPlay(audioUrl, result.id, selectedProfileId, data.text.substring(0, 50));
form.reset();
options.onSuccess?.(result.id);
} catch (error) {
toast({
@@ -108,7 +175,6 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
variant: 'destructive',
});
} finally {
setIsGenerating(false);
setDownloadingModelName(null);
setDownloadingDisplayName(null);
}
+155
View File
@@ -0,0 +1,155 @@
import { useQueryClient } from '@tanstack/react-query';
import { useEffect, useRef } from 'react';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import { useGenerationStore } from '@/stores/generationStore';
import { usePlayerStore } from '@/stores/playerStore';
import { useServerStore } from '@/stores/serverStore';
interface GenerationStatusEvent {
id: string;
status: 'loading_model' | 'generating' | 'completed' | 'failed' | 'not_found';
duration?: number;
error?: string;
}
/**
* Subscribes to SSE for all pending generations. When a generation completes,
* invalidates the history query, removes it from pending, and auto-plays
* if the player is idle.
*/
export function useGenerationProgress() {
const queryClient = useQueryClient();
const { toast } = useToast();
const pendingIds = useGenerationStore((s) => s.pendingGenerationIds);
const removePendingGeneration = useGenerationStore((s) => s.removePendingGeneration);
const removePendingStoryAdd = useGenerationStore((s) => s.removePendingStoryAdd);
const isPlaying = usePlayerStore((s) => s.isPlaying);
const setAudioWithAutoPlay = usePlayerStore((s) => s.setAudioWithAutoPlay);
const autoplayOnGenerate = useServerStore((s) => s.autoplayOnGenerate);
// Keep refs to avoid stale closures in EventSource handlers
const isPlayingRef = useRef(isPlaying);
const autoplayRef = useRef(autoplayOnGenerate);
isPlayingRef.current = isPlaying;
autoplayRef.current = autoplayOnGenerate;
// Track active EventSource instances
const eventSourcesRef = useRef<Map<string, EventSource>>(new Map());
// Unmount-only cleanup — close all SSE connections when the hook is torn down
useEffect(() => {
const sources = eventSourcesRef.current;
return () => {
for (const source of sources.values()) {
source.close();
}
sources.clear();
};
}, []);
useEffect(() => {
const currentSources = eventSourcesRef.current;
// Close SSE connections for IDs no longer pending
for (const [id, source] of currentSources.entries()) {
if (!pendingIds.has(id)) {
source.close();
currentSources.delete(id);
}
}
// Open SSE connections for new pending IDs
for (const id of pendingIds) {
if (currentSources.has(id)) continue;
const url = apiClient.getGenerationStatusUrl(id);
const source = new EventSource(url);
source.onmessage = (event) => {
try {
const data: GenerationStatusEvent = JSON.parse(event.data);
if (data.status === 'completed') {
source.close();
currentSources.delete(id);
removePendingGeneration(id);
// Refetch history to pick up the completed generation
queryClient.refetchQueries({ queryKey: ['history'] });
// If this generation was queued for a story, add it now
const storyId = removePendingStoryAdd(id);
if (storyId) {
apiClient
.addStoryItem(storyId, { generation_id: id })
.then(() => {
queryClient.invalidateQueries({ queryKey: ['stories'] });
queryClient.invalidateQueries({ queryKey: ['stories', storyId] });
toast({
title: 'Added to story',
description: data.duration
? `Audio generated (${data.duration.toFixed(2)}s) and added to story`
: 'Audio generated and added to story',
});
})
.catch(() => {
toast({
title: 'Generation complete',
description: 'Audio generated but failed to add to story',
variant: 'destructive',
});
});
} else {
// toast({
// title: 'Generation complete!',
// description: data.duration
// ? `Audio generated (${data.duration.toFixed(2)}s)`
// : 'Audio generated',
// });
}
// Auto-play if enabled and nothing is currently playing
if (autoplayRef.current && !isPlayingRef.current) {
const genAudioUrl = apiClient.getAudioUrl(id);
setAudioWithAutoPlay(genAudioUrl, id, '', '');
}
} else if (data.status === 'failed' || data.status === 'not_found') {
source.close();
currentSources.delete(id);
removePendingGeneration(id);
removePendingStoryAdd(id);
queryClient.refetchQueries({ queryKey: ['history'] });
toast({
title: data.status === 'not_found' ? 'Generation not found' : 'Generation failed',
description: data.error || 'An error occurred during generation',
variant: 'destructive',
});
}
} catch {
// Ignore parse errors from heartbeats etc
}
};
source.onerror = () => {
// SSE connection dropped — clean up and refresh history so any
// completed/failed generation still appears in the list
source.close();
currentSources.delete(id);
removePendingGeneration(id);
queryClient.refetchQueries({ queryKey: ['history'] });
};
currentSources.set(id, source);
}
}, [
pendingIds,
removePendingGeneration,
removePendingStoryAdd,
queryClient,
toast,
setAudioWithAutoPlay,
]);
}
+11
View File
@@ -29,6 +29,17 @@ export function useDeleteGeneration() {
});
}
export function useClearFailedGenerations() {
const queryClient = useQueryClient();
return useMutation({
mutationFn: () => apiClient.clearFailedGenerations(),
onSuccess: () => {
queryClient.invalidateQueries({ queryKey: ['history'] });
},
});
}
export function useExportGeneration() {
const platform = usePlatform();
+5 -5
View File
@@ -10,7 +10,7 @@ interface UseModelDownloadToastOptions {
displayName: string;
enabled?: boolean;
onComplete?: () => void;
onError?: () => void;
onError?: (error: string) => void;
}
/**
@@ -101,7 +101,7 @@ export function useModelDownloadToast({
break;
case 'error':
statusIcon = <XCircle className="h-4 w-4 text-destructive" />;
statusText = `Error: ${progress.error || 'Unknown error'}`;
statusText = 'Download failed. See Problems panel for details.';
break;
case 'downloading':
statusIcon = <Loader2 className="h-4 w-4 animate-spin" />;
@@ -131,8 +131,8 @@ export function useModelDownloadToast({
)}
</div>
),
duration: progress.status === 'complete' ? 5000 : Infinity,
variant: progress.status === 'error' ? 'destructive' : 'default',
duration:
progress.status === 'complete' || progress.status === 'error' ? 5000 : Infinity,
});
// Close connection and dismiss toast on completion or error
@@ -169,7 +169,7 @@ export function useModelDownloadToast({
onComplete();
} else if (isError && onError) {
console.log('[useModelDownloadToast] Download error, calling onError callback');
onError();
onError(progress.error || 'Unknown error');
}
}
}
+12 -12
View File
@@ -1,23 +1,23 @@
import { useCallback, useEffect, useRef, useState } from 'react';
import { apiClient } from '@/lib/api/client';
import { useGenerationStore } from '@/stores/generationStore';
import type { ActiveDownloadTask } from '@/lib/api/types';
import { useGenerationStore } from '@/stores/generationStore';
// Polling interval in milliseconds
const POLL_INTERVAL = 2000;
const POLL_INTERVAL = 30000;
/**
* Hook to monitor active tasks (downloads and generations).
* Polls the server periodically to catch downloads triggered from anywhere
* (transcription, generation, explicit download, etc.).
*
*
* Returns the active downloads so components can render download toasts.
*/
export function useRestoreActiveTasks() {
const [activeDownloads, setActiveDownloads] = useState<ActiveDownloadTask[]>([]);
const setIsGenerating = useGenerationStore((state) => state.setIsGenerating);
const setActiveGenerationId = useGenerationStore((state) => state.setActiveGenerationId);
const addPendingGeneration = useGenerationStore((state) => state.addPendingGeneration);
// Track which downloads we've seen to detect new ones
const seenDownloadsRef = useRef<Set<string>>(new Set());
@@ -25,15 +25,15 @@ export function useRestoreActiveTasks() {
try {
const tasks = await apiClient.getActiveTasks();
// Update generation state
// Restore pending generations (e.g., after page refresh)
if (tasks.generations.length > 0) {
setIsGenerating(true);
setActiveGenerationId(tasks.generations[0].task_id);
for (const gen of tasks.generations) {
addPendingGeneration(gen.task_id);
}
} else {
// Only clear if we were tracking a generation
const currentId = useGenerationStore.getState().activeGenerationId;
if (currentId) {
setIsGenerating(false);
setActiveGenerationId(null);
}
}
@@ -41,14 +41,14 @@ export function useRestoreActiveTasks() {
// Update active downloads
// Keep track of all active downloads (including new ones)
const currentDownloadNames = new Set(tasks.downloads.map((d) => d.model_name));
// Remove completed downloads from our seen set
for (const name of seenDownloadsRef.current) {
if (!currentDownloadNames.has(name)) {
seenDownloadsRef.current.delete(name);
}
}
// Add new downloads to seen set
for (const download of tasks.downloads) {
seenDownloadsRef.current.add(download.model_name);
@@ -59,7 +59,7 @@ export function useRestoreActiveTasks() {
// Silently fail - server might be temporarily unavailable
console.debug('Failed to fetch active tasks:', error);
}
}, [setIsGenerating, setActiveGenerationId]);
}, [setActiveGenerationId, addPendingGeneration]);
useEffect(() => {
// Fetch immediately on mount
+61 -8
View File
@@ -1,6 +1,15 @@
import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query';
import { apiClient } from '@/lib/api/client';
import type { StoryCreate, StoryItemCreate, StoryItemBatchUpdate, StoryItemReorder, StoryItemMove, StoryItemTrim, StoryItemSplit } from '@/lib/api/types';
import type {
StoryCreate,
StoryItemBatchUpdate,
StoryItemCreate,
StoryItemMove,
StoryItemReorder,
StoryItemSplit,
StoryItemTrim,
StoryItemVersionUpdate,
} from '@/lib/api/types';
import { usePlatform } from '@/platform/PlatformContext';
export function useStories() {
@@ -109,8 +118,15 @@ export function useMoveStoryItem() {
const queryClient = useQueryClient();
return useMutation({
mutationFn: ({ storyId, itemId, data }: { storyId: string; itemId: string; data: StoryItemMove }) =>
apiClient.moveStoryItem(storyId, itemId, data),
mutationFn: ({
storyId,
itemId,
data,
}: {
storyId: string;
itemId: string;
data: StoryItemMove;
}) => apiClient.moveStoryItem(storyId, itemId, data),
onSuccess: (_, variables) => {
queryClient.invalidateQueries({ queryKey: ['stories'] });
queryClient.invalidateQueries({ queryKey: ['stories', variables.storyId] });
@@ -122,8 +138,15 @@ export function useTrimStoryItem() {
const queryClient = useQueryClient();
return useMutation({
mutationFn: ({ storyId, itemId, data }: { storyId: string; itemId: string; data: StoryItemTrim }) =>
apiClient.trimStoryItem(storyId, itemId, data),
mutationFn: ({
storyId,
itemId,
data,
}: {
storyId: string;
itemId: string;
data: StoryItemTrim;
}) => apiClient.trimStoryItem(storyId, itemId, data),
onSuccess: (_, variables) => {
queryClient.invalidateQueries({ queryKey: ['stories'] });
queryClient.invalidateQueries({ queryKey: ['stories', variables.storyId] });
@@ -135,8 +158,15 @@ export function useSplitStoryItem() {
const queryClient = useQueryClient();
return useMutation({
mutationFn: ({ storyId, itemId, data }: { storyId: string; itemId: string; data: StoryItemSplit }) =>
apiClient.splitStoryItem(storyId, itemId, data),
mutationFn: ({
storyId,
itemId,
data,
}: {
storyId: string;
itemId: string;
data: StoryItemSplit;
}) => apiClient.splitStoryItem(storyId, itemId, data),
onSuccess: (_, variables) => {
queryClient.invalidateQueries({ queryKey: ['stories'] });
queryClient.invalidateQueries({ queryKey: ['stories', variables.storyId] });
@@ -157,6 +187,26 @@ export function useDuplicateStoryItem() {
});
}
export function useSetStoryItemVersion() {
const queryClient = useQueryClient();
return useMutation({
mutationFn: ({
storyId,
itemId,
data,
}: {
storyId: string;
itemId: string;
data: StoryItemVersionUpdate;
}) => apiClient.setStoryItemVersion(storyId, itemId, data),
onSuccess: (_, variables) => {
queryClient.invalidateQueries({ queryKey: ['stories'] });
queryClient.invalidateQueries({ queryKey: ['stories', variables.storyId] });
},
});
}
export function useExportStoryAudio() {
const platform = usePlatform();
@@ -165,7 +215,10 @@ export function useExportStoryAudio() {
const blob = await apiClient.exportStoryAudio(storyId);
// Create safe filename
const safeName = storyName.substring(0, 50).replace(/[^a-z0-9]/gi, '-').toLowerCase();
const safeName = storyName
.substring(0, 50)
.replace(/[^a-z0-9]/gi, '-')
.toLowerCase();
const filename = `${safeName || 'story'}.wav`;
await platform.filesystem.saveFile(filename, blob, [
+23 -11
View File
@@ -70,6 +70,16 @@ export function useStoryPlayback(items: StoryItemDetail[] | undefined) {
}
}, []);
// Resolve the audio buffer key and URL for an item.
// When a version_id is pinned, use that version's audio; otherwise use the generation default.
const getAudioKey = (item: StoryItemDetail) =>
item.version_id ? `v:${item.version_id}` : item.generation_id;
const getAudioUrlForItem = (item: StoryItemDetail) =>
item.version_id
? apiClient.getVersionAudioUrl(item.version_id)
: apiClient.getAudioUrl(item.generation_id);
// Preload audio files as AudioBuffers
useEffect(() => {
if (!items || items.length === 0) {
@@ -78,12 +88,12 @@ export function useStoryPlayback(items: StoryItemDetail[] | undefined) {
return;
}
const currentIds = new Set(items.map((item) => item.generation_id));
const currentKeys = new Set(items.map(getAudioKey));
const audioContext = getAudioContext();
// Remove buffers for items that no longer exist
for (const [id] of audioBuffersRef.current) {
if (!currentIds.has(id)) {
if (!currentKeys.has(id)) {
audioBuffersRef.current.delete(id);
}
}
@@ -91,24 +101,25 @@ export function useStoryPlayback(items: StoryItemDetail[] | undefined) {
// Preload audio for new items
const preloadPromises: Promise<void>[] = [];
for (const item of items) {
if (!audioBuffersRef.current.has(item.generation_id)) {
const audioUrl = apiClient.getAudioUrl(item.generation_id);
console.log('[StoryPlayback] Preloading audio buffer:', item.generation_id);
const key = getAudioKey(item);
if (!audioBuffersRef.current.has(key)) {
const audioUrl = getAudioUrlForItem(item);
console.log('[StoryPlayback] Preloading audio buffer:', key);
const preloadPromise = fetch(audioUrl)
.then((response) => response.arrayBuffer())
.then((arrayBuffer) => audioContext.decodeAudioData(arrayBuffer))
.then((audioBuffer) => {
audioBuffersRef.current.set(item.generation_id, audioBuffer);
audioBuffersRef.current.set(key, audioBuffer);
console.log(
'[StoryPlayback] Preloaded buffer:',
item.generation_id,
key,
'duration:',
audioBuffer.duration,
);
})
.catch((err) => {
console.error('[StoryPlayback] Failed to preload audio:', item.generation_id, err);
console.error('[StoryPlayback] Failed to preload audio:', key, err);
});
preloadPromises.push(preloadPromise);
@@ -216,15 +227,16 @@ export function useStoryPlayback(items: StoryItemDetail[] | undefined) {
// Schedule new sources for items that should be playing
for (const item of shouldBePlaying) {
if (!activeSourcesRef.current.has(item.id)) {
const buffer = audioBuffersRef.current.get(item.generation_id);
const bufferKey = getAudioKey(item);
const buffer = audioBuffersRef.current.get(bufferKey);
if (!buffer) {
console.warn('[StoryPlayback] Buffer not loaded for:', item.generation_id);
console.warn('[StoryPlayback] Buffer not loaded for:', bufferKey);
continue;
}
// Calculate when this item should start in AudioContext time
const itemStartContextTime = storyTimeToContextTime(item.start_time_ms);
// Calculate effective duration and trim offsets
const trimStartSec = (item.trim_start_ms || 0) / 1000;
const trimEndSec = (item.trim_end_ms || 0) / 1000;
+22 -8
View File
@@ -1,4 +1,4 @@
import { useState, useRef, useCallback, useEffect } from 'react';
import { useCallback, useEffect, useRef, useState } from 'react';
import { usePlatform } from '@/platform/PlatformContext';
interface UseSystemAudioCaptureOptions {
@@ -26,8 +26,24 @@ export function useSystemAudioCapture({
// Check if system audio capture is supported
useEffect(() => {
const supported = platform.audio.isSystemAudioSupported();
setIsSupported(supported);
let isActive = true;
void platform.audio
.isSystemAudioSupported()
.then((supported) => {
if (isActive) {
setIsSupported(supported);
}
})
.catch(() => {
if (isActive) {
setIsSupported(false);
}
});
return () => {
isActive = false;
};
}, [platform]);
const startRecording = useCallback(async () => {
@@ -94,15 +110,13 @@ export function useSystemAudioCapture({
const blob = await platform.audio.stopSystemAudioCapture();
// Pass the actual recorded duration
const recordedDuration = startTimeRef.current
? (Date.now() - startTimeRef.current) / 1000
const recordedDuration = startTimeRef.current
? (Date.now() - startTimeRef.current) / 1000
: undefined;
onRecordingComplete?.(blob, recordedDuration);
} catch (err) {
const errorMessage =
err instanceof Error
? err.message
: 'Failed to stop system audio capture.';
err instanceof Error ? err.message : 'Failed to stop system audio capture.';
setError(errorMessage);
}
}, [isRecording, onRecordingComplete, platform]);
+10 -2
View File
@@ -1,10 +1,18 @@
import { useMutation } from '@tanstack/react-query';
import { apiClient } from '@/lib/api/client';
import type { WhisperModelSize } from '@/lib/api/types';
import type { LanguageCode } from '@/lib/constants/languages';
export function useTranscription() {
return useMutation({
mutationFn: ({ file, language }: { file: File; language?: LanguageCode }) =>
apiClient.transcribeAudio(file, language),
mutationFn: ({
file,
language,
model,
}: {
file: File;
language?: LanguageCode;
model?: WhisperModelSize;
}) => apiClient.transcribeAudio(file, language, model),
});
}
+19
View File
@@ -0,0 +1,19 @@
import { QueryClient } from '@tanstack/react-query';
/**
* Shared QueryClient instance used across the app.
*
* Extracted into its own side-effect-free module so it can be imported from
* both the React bootstrap (main.tsx) and non-React code (stores, utilities)
* without pulling in ReactDOM or other bootstrap side effects.
*/
export const queryClient = new QueryClient({
defaultOptions: {
queries: {
staleTime: 1000 * 60 * 5, // 5 minutes
gcTime: 1000 * 60 * 10, // 10 minutes (formerly cacheTime)
retry: 1,
refetchOnWindowFocus: false,
},
},
});
+36 -18
View File
@@ -22,6 +22,11 @@ export function formatAudioDuration(seconds: number): string {
* If the file has a recordedDuration property (from recording hooks),
* use that instead of trying to read metadata. This fixes issues on Windows
* where WebM files from MediaRecorder don't have proper duration metadata.
*
* For uploaded files we use AudioContext.decodeAudioData which fully decodes
* the audio and returns the exact duration. This is more reliable than
* HTMLMediaElement.duration which can return incorrect large values for VBR
* MP3 files that lack a proper XING/VBRI header.
*/
export async function getAudioDuration(
file: File & { recordedDuration?: number },
@@ -30,26 +35,39 @@ export async function getAudioDuration(
return file.recordedDuration;
}
return new Promise((resolve, reject) => {
const audio = new Audio();
const url = URL.createObjectURL(file);
// Use Web Audio API for accurate duration — avoids VBR MP3 metadata issues.
try {
const audioContext = new AudioContext();
try {
const arrayBuffer = await file.arrayBuffer();
const audioBuffer = await audioContext.decodeAudioData(arrayBuffer);
return audioBuffer.duration;
} finally {
await audioContext.close();
}
} catch {
// Fallback: read duration from the media element (less accurate but works for WAV).
return new Promise((resolve, reject) => {
const audio = new Audio();
const url = URL.createObjectURL(file);
audio.addEventListener('loadedmetadata', () => {
URL.revokeObjectURL(url);
if (Number.isFinite(audio.duration) && audio.duration > 0) {
resolve(audio.duration);
} else {
reject(new Error('Audio file has invalid duration metadata'));
}
audio.addEventListener('loadedmetadata', () => {
URL.revokeObjectURL(url);
if (Number.isFinite(audio.duration) && audio.duration > 0) {
resolve(audio.duration);
} else {
reject(new Error('Audio file has invalid duration metadata'));
}
});
audio.addEventListener('error', () => {
URL.revokeObjectURL(url);
reject(new Error('Failed to load audio file'));
});
audio.src = url;
});
audio.addEventListener('error', () => {
URL.revokeObjectURL(url);
reject(new Error('Failed to load audio file'));
});
audio.src = url;
});
}
}
/**
+16 -1
View File
@@ -21,10 +21,25 @@ export function formatDate(date: string | Date): string {
} else {
dateObj = date;
}
return formatDistance(dateObj, new Date(), { addSuffix: true }).replace(/^about /i, '');
}
const ENGINE_DISPLAY_NAMES: Record<string, string> = {
qwen: 'Qwen',
luxtts: 'LuxTTS',
chatterbox: 'Chatterbox',
chatterbox_turbo: 'Chatterbox Turbo',
};
export function formatEngineName(engine?: string, modelSize?: string): string {
const name = ENGINE_DISPLAY_NAMES[engine ?? 'qwen'] ?? engine ?? 'Qwen';
if (engine === 'qwen' && modelSize) {
return `${name} ${modelSize}`;
}
return name;
}
export function formatFileSize(bytes: number): string {
if (bytes === 0) return '0 Bytes';
const k = 1024;
+37
View File
@@ -0,0 +1,37 @@
export interface ChangelogEntry {
version: string;
date: string | null;
body: string;
}
/**
* Parses a Keep-a-Changelog style markdown string into structured entries.
*
* Splits on `## [version]` headings and extracts the version + date from each.
* The body is the raw markdown between headings (trimmed), with the leading
* `# Changelog` title and trailing link references stripped.
*/
export function parseChangelog(raw: string): ChangelogEntry[] {
const entries: ChangelogEntry[] = [];
// Strip trailing link reference definitions (e.g. [0.1.0]: https://...)
const cleaned = raw.replace(/^\[[\w.]+\]:.*$/gm, '').trimEnd();
// Match `## [version]` or `## [version] - date`
const headingRe = /^## \[(.+?)\](?:\s*-\s*(.+))?$/gm;
const matches = [...cleaned.matchAll(headingRe)];
for (let i = 0; i < matches.length; i++) {
const match = matches[i];
const version = match[1];
const date = match[2]?.trim() || null;
const start = match.index! + match[0].length;
const end = i + 1 < matches.length ? matches[i + 1].index! : cleaned.length;
const body = cleaned.slice(start, end).trim();
entries.push({ version, date, body });
}
return entries;
}
+2 -12
View File
@@ -1,20 +1,10 @@
import { QueryClient, QueryClientProvider } from '@tanstack/react-query';
import { QueryClientProvider } from '@tanstack/react-query';
// import { ReactQueryDevtools } from '@tanstack/react-query-devtools';
import React from 'react';
import ReactDOM from 'react-dom/client';
import App from './App';
import './index.css';
const queryClient = new QueryClient({
defaultOptions: {
queries: {
staleTime: 1000 * 60 * 5, // 5 minutes
gcTime: 1000 * 60 * 10, // 10 minutes (formerly cacheTime)
retry: 1,
refetchOnWindowFocus: false,
},
},
});
import { queryClient } from './lib/queryClient';
ReactDOM.createRoot(document.getElementById('root')!).render(
<React.StrictMode>
+1 -5
View File
@@ -9,11 +9,7 @@ export interface PlatformProviderProps {
}
export function PlatformProvider({ platform, children }: PlatformProviderProps) {
return (
<PlatformContext.Provider value={platform}>
{children}
</PlatformContext.Provider>
);
return <PlatformContext.Provider value={platform}>{children}</PlatformContext.Provider>;
}
export function usePlatform(): Platform {
+11 -2
View File
@@ -10,6 +10,8 @@ export interface FileFilter {
export interface PlatformFilesystem {
saveFile(filename: string, blob: Blob, filters?: FileFilter[]): Promise<void>;
openPath(path: string): Promise<void>;
pickDirectory(title: string): Promise<string | null>;
}
export interface UpdateStatus {
@@ -40,7 +42,7 @@ export interface AudioDevice {
}
export interface PlatformAudio {
isSystemAudioSupported(): boolean;
isSystemAudioSupported(): Promise<boolean>;
startSystemAudioCapture(maxDurationSecs: number): Promise<void>;
stopSystemAudioCapture(): Promise<Blob>;
listOutputDevices(): Promise<AudioDevice[]>;
@@ -48,11 +50,18 @@ export interface PlatformAudio {
stopPlayback(): void;
}
export interface ServerLogEntry {
stream: 'stdout' | 'stderr';
line: string;
}
export interface PlatformLifecycle {
startServer(remote?: boolean): Promise<string>;
startServer(remote?: boolean, modelsDir?: string | null): Promise<string>;
stopServer(): Promise<void>;
restartServer(modelsDir?: string | null): Promise<string>;
setKeepServerRunning(keep: boolean): Promise<void>;
setupWindowCloseHandler(): Promise<void>;
subscribeToServerLogs(callback: (entry: ServerLogEntry) => void): () => void;
onServerReady?: () => void;
}

Some files were not shown because too many files have changed in this diff Show More