- 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
- 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
- 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
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.
- 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
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
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.
- 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
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
- 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
- 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
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
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
- 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
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.
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
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).
- 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)
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.
soundfile cannot infer format from .tmp extension, causing all
generations to fail with 'No format specified and unable to get
format from file extension'
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.
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
