Dep swap:
- Drop the git-pinned jamiepine/rdev fork we were carrying since the
upstream crate is abandoned.
- Depend on keytap 0.2 from crates.io — our own cross-platform global
keyboard tap crate. Clean shutdown via Drop, Sonoma-safe by design
(no TSMGetInputSourceProperty calls off the main thread, so
`set_is_main_thread(false)` is gone), and properly versioned.
Chord engine rewrite:
- Delete hotkey_monitor.rs's internal Chord state machine (Match enum,
KeyEvent enum, step()/classify() methods, associated unit tests).
keytap's ChordMatcher subsumes it: Momentary chord for PTT,
add_toggle() for Toggle-to-talk, longest-match resolution, sticky-end
for Toggle. Net: -80 LOC in hotkey_monitor.rs; the remaining module
is the dispatcher loop + Effect→Tauri translation.
- Preserve the PTT→Toggle "RestartRecording" upgrade signal. keytap
emits End(PTT)+Start(Toggle) atomically (same Instant) when the held
set upgrades from a shorter chord to a longer superset. The
dispatcher peeks at the matcher with a 5 ms recv_timeout after any
End and coalesces the pair into Effect::RestartRecording so the
frontend still gets the "discard the transition-moment audio" signal
instead of an unrelated Stop+Start pair.
- HotkeyMonitor::update_bindings now actually tears down the tap on
empty bindings instead of leaving an idle CGEventTap around. New
bindings rebuild the matcher and the dispatcher thread from scratch.
key_codes.rs:
- Rewrite the browser-code → Key table against keytap's cleaner Key
variant names (`A`..`Z` not `KeyA`..`KeyZ`, `Digit0`..`Digit9` not
`Num0`..`Num9`, `ArrowUp` not `UpArrow`, `AltLeft`/`AltRight` instead
of `Alt`/`AltGr`, `Period` not `Dot`, …). On-disk chord string
format (W3C `KeyboardEvent.code` identifiers) is unchanged, so
capture_settings rows written before the swap round-trip identically.
Legacy aliases (`Alt`, `AltGr`, `Num0`, `UpArrow`, `Dot`, …) kept for
forward-compat on old rows.
main.rs / input_monitoring.rs:
- Update the few doc comments that referenced `rdev::listen` to
describe keytap's Tap; no behavioural change.
- build_chord_bindings now imports from keytap::Key.
- enable_hotkey / disable_hotkey / update_chord_bindings reach into
HotkeyMonitor via &mut since apply()/update_bindings() now mutate.
Tests live in keytap now (22 chord-related tests in keytap 0.2,
including the PTT→Toggle upgrade scenario that used to be tested in
hotkey_monitor.rs). Voicebox's hotkey_monitor.rs is thin enough that
local testing would be trivia.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
Two reliability gaps in the /events/speak subscriber:
1. resp.chunk().await had no idle timeout. A backend that accepts the
TCP connection but stops producing frames (deadlocked SSE endpoint,
zombie process) would block the task forever without reconnecting.
The pill window would never surface for agent-initiated speech and
there would be nothing to log. Backend emits a `:ping` heartbeat
every 15 s, so 45 s without any data is now treated as a dead
stream — the task errors out and the reconnect loop takes over.
2. Flat 2 s backoff escalates nowhere. Logs fill with reconnect lines
when the backend is down for minutes, and a backend that accepts +
immediately closes connections (no data) spins the loop tightly.
Backoff now escalates 500 ms → 30 s on unproductive rounds and
resets only when at least one frame arrives (the connection was
genuinely productive, not just accepted).
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
Two bugs in paste_final_text' clipboard handling:
1. Restore was unconditional. If the user ⌘C'd in the target app during
the 400 ms paste-consume window — or a clipboard history tool (Paste,
Pastebot, Maccy) or Universal Clipboard sync snapshotted our staged
text — the blind restore overwrote their newer content with the
pre-paste snapshot, silently losing user data.
2. send_paste' errors were propagated with ? before the restore, so a
CGEventPost / SendInput failure left the user's clipboard stuck on
the transcript.
Fix folds both into one pattern: capture the post-write change count,
re-read it after paste-consume, restore only when they match (plus treat
a change-count read failure as "unknown, don't overwrite"). Isolate
send_paste's error so the restore runs regardless of paste success, then
propagate the paste error after.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
macOS 14 deprecated NSRunningApplication.activateWithOptions: in favour
of a cooperative-activation pattern: the caller first yields activation
rights to the target, then the target activate()s against the tightened
Sonoma foreground rules. Without the yield, activate() on 14+ sometimes
silently fails or only bounces the dock icon — the exact "paste lands in
the wrong app" symptom we were previously one API break away from.
activate_pid now discovers the 14+ selector via respondsToSelector: and
branches: on 14+ it yieldActivationToApplication:'s from
NSRunningApplication.current then calls -activate on the target; on
11–13 it stays on -activateWithOptions: (still the only option). Both
branches propagate the BOOL return — if activation is refused we error
out before clobbering the clipboard instead of silently proceeding.
The respondsToSelector: result is cached in a OnceLock so the probe
isn't repeated on every paste.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
macOS apps match Cmd+V against the layout-translated character via NSMenu
key equivalents, so posting kVK_ANSI_V (= 9, the QWERTY V position) on
Dvorak produces Cmd+. and never triggers Paste. New keyboard_layout
module resolves the active layout's V keycode via
TISCopyCurrentKeyboardLayoutInputSource + UCKeyTranslate, caches it in an
AtomicU16, and refreshes on kTISNotifySelectedKeyboardInputSourceChanged.
All TIS calls run on the main thread (init from Tauri setup; observer
callback delivered to the main runloop); synthetic_keys::send_paste
reads the cached value once per paste. Falls back to kVK_ANSI_V when
resolution fails or the active input source carries no Unicode key
layout data.
Windows is intentionally left on hardcoded VK_V — SendInput delivers
WM_KEYDOWN with wParam = VK_V to the target regardless of the active
layout, which is why `Send "^v"` works for AutoHotkey on Dvorak Windows.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
The pill window now surfaces for agent-initiated speech without main-window
involvement. Rust subscribes to /events/speak via a tokio task + reqwest
streaming body (speak_monitor.rs), shows the pill, and forwards events to
the dictate webview over Tauri's event bus. The pill plays audio via a
plain HTMLAudioElement and emits dictate:hide when playback ends. The
pill stays hidden through the ~1 s generation wait and only surfaces when
audio actually starts, with the counter armed at that moment.
Fixes a shared-dict mutation in mcp_server/events.publish() that caused
the second subscriber (Rust speak_monitor) to receive `event: message`
instead of named speak-start/speak-end frames. Also teaches the speak_monitor
parser to handle CRLF framing (sse-starlette default). Main-window
AudioPlayer now skips autoplay for source in {mcp, rest} to avoid
double-play when both windows are alive.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
Ships the Capture release end to end. Global-hotkey dictation with
synthetic paste into the focused app on macOS and Windows, an on-screen
pill across recording / transcribing / refining, customizable push-to-
talk and toggle chords, and an accessibility-permission prompt scoped to
Settings → Captures with inline re-check feedback.
Voice profiles gain optional personalities that power compose / rewrite /
respond actions via a local Qwen3 LLM — shared with refinement, so there
is one local LLM in the app, not two.
Refinement hardened with deterministic Whisper-loop collapse before the
LLM sees the transcript, per-capture flag snapshots for re-runs, and a
ten-transcript evaluation harness across every bundled refinement size.
Version bump 0.4.5 → 0.5.0.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
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).
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]>
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).
- 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
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
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
- 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)
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
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
- 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
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
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
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]>
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]>
- Added support for MLX backend on Apple Silicon, enabling optimized performance for TTS and STT tasks.
- Implemented platform detection to dynamically select between MLX and PyTorch based on the runtime environment.
- Updated build process to include MLX-specific dependencies and configurations for macOS.
- Refactored backend code to improve model loading and inference logic, accommodating backend-specific requirements.
- Enhanced documentation to clarify backend selection and performance benefits for different platforms.
- Streamlined installation instructions and troubleshooting guidance for MLX-related issues.
- Created a new .npmrc file to enforce bun usage.
- Bumped version numbers for multiple packages to 0.1.9 in bun.lock.
- Added react-sound-visualizer dependency to enhance audio visualization features.
- Introduced convert:assets script in package.json for asset optimization.
- Updated CONTRIBUTING.md with instructions for converting assets to web formats.
- Added documentation files for API endpoints and developer guidelines in the docs directory.
- Added a new `/shutdown` endpoint to allow graceful server shutdown via HTTP.
- Implemented process tree management functions to handle child processes during shutdown on Windows.
- Updated the `stop_server` function to attempt graceful shutdown before forcefully terminating processes.
- Enhanced error handling and logging for shutdown operations.
Previously, running `bun run dev` would fail because Tauri requires
the sidecar binary to exist at compile time, even in development mode.
This forced developers to build the full PyInstaller binary before
they could start development.
This change introduces a streamlined dev workflow:
1. Add `scripts/setup-dev-sidecar.js` - Creates minimal placeholder
binaries that satisfy Tauri's compile-time check. Works cross-platform
(Windows PE stub, Unix shell script).
2. Update Rust code to gracefully handle dev mode - When the sidecar
fails to start, it checks if a manually-started server is already
running on the expected port and connects to it instead.
3. Update npm scripts - `bun run dev` now auto-runs the setup script,
and `dev:server` uses the correct port (17493).
4. Update CONTRIBUTING.md with clearer dev workflow documentation.
New development workflow:
Terminal 1: bun run dev:server
Terminal 2: bun run dev
The bundled binary is only required for production builds.
- Introduced a stop flag mechanism to manage audio playback more effectively.
- Enhanced native playback logic to ensure proper stopping of existing streams before starting new playback.
- Updated error handling and logging for better visibility during playback operations.
- Refactored audio output handling in Rust to support stopping playback and outputting silence when required.
- Improved the integration of native playback with WaveSurfer for seamless audio visualization.
- Improved the useNativePlayback logic to include detailed console logging for better debugging.
- Updated auto-play functionality to fetch runtime profile channels and channels, ensuring accurate playback decisions.
- Refactored audio playback handling to support native audio routing with enhanced error handling and logging.
- Introduced a new MultiSelect component for improved channel selection in VoicesTab.
- Updated FloatingGenerateBox to include selectedProfileId in audio setting.
- Added new dependencies for audio processing in Cargo.toml and Cargo.lock.
- Introduced the FloatingGenerateBox component for audio generation, enhancing user interaction with voice profiles.
- Updated App component to integrate FloatingGenerateBox and removed the GenerationForm component.
- Enhanced the layout for better responsiveness and added functionality to manage audio playback state.
- Updated UpdateStatus component to include new update handling logic and improved UI feedback for update readiness.
- Added support for capturing system audio on Windows using WASAPI with improved error handling and thread safety.
- Introduced the 'scopeguard' crate for better resource management during audio capture.
- Updated Cargo.toml to include 'scopeguard' and modified Windows-specific dependencies for enhanced functionality.
- Added a new test for validating audio capture output, ensuring the captured audio data is valid and non-empty.
- Removed console logging from the useSystemAudioCapture hook to streamline the code.
- Introduced error handling in the audio capture state to capture and report errors more effectively.
- Updated the cleanup logic to ensure proper handling of errors during audio capture on unmount.
- Enhanced error messages for better clarity when audio capture fails.
- Added the `com.apple.security.device.audio-input` entitlement to the Entitlements.plist for improved audio capture capabilities.
- Refactored the audio sample extraction logic in macOS to handle both interleaved and planar audio formats, improving sample processing and interleaving of channels.
- Updated the Assets.car file to reflect changes in the audio capture implementation.
- Added new components for managing audio channels, including creation, updating, and deletion of channels.
- Introduced a new AudioTab for channel management and integrated it into the main application layout.
- Updated the API client to support audio channel operations and added corresponding backend endpoints.
- Enhanced the player store to handle audio playback routing through assigned channels.
- Refactored existing components to accommodate the new audio channel functionality, including updates to the HistoryTable and GenerationForm for profile-channel associations.
- Improved sidebar navigation to include new tabs for Voices and Audio management.
- Introduced AtomicBool for stop signal handling to improve thread safety.
- Updated audio capture logic to utilize WASAPI more effectively, including error handling and buffer management.
- Enhanced the spawn mechanism for audio capture tasks to ensure compatibility with non-Send types.
- Added a new dependency on the 'windows' crate in Cargo.lock for improved functionality.
- Added support for generating a multi-size Windows icon (icon.ico) in the update-icons.sh script.
- Updated Cargo.toml to include the 'windows' crate with specific features for Windows support.
- Bumped version of the 'voicebox' package from 0.1.0 to 0.1.1 in Cargo.lock.
- Updated .gitignore to exclude the generated Assets.car file.
- Updated the server management logic in main.rs to include the PID of the existing voicebox server when reusing it, enhancing clarity in logging.
- Improved the formatting of imports in App.tsx for better readability.
- Added logic in main.rs to check for an existing voicebox server running on the designated port, allowing reuse of the server if found.
- Enhanced the build.rs script by improving formatting and readability of the Swift library path definitions.
- Updated logging to provide clearer warnings when the icon source is not found during the build process.
Jamie Pine