mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-26 13:45:16 -07:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 James PineandClaude Opus 4.7
|
a6ac8ceba7 | ||
|
James PineandClaude Opus 4.7
|
a179b826cd | ||
|
James PineandClaude Opus 4.7
|
a641ffc919 | ||
|
James PineandClaude Opus 4.7
|
f267cafb80 | ||
|
James PineandClaude Opus 4.7
|
83cc172f71 | ||
|
James PineandClaude Opus 4.7
|
d7285bf23a | ||
|
James PineandClaude Opus 4.7
|
13924741a7 | ||
|
James PineandClaude Opus 4.7
|
1ca0756dc1 | ||
|
James PineandClaude Opus 4.7
|
cf17d94441 |
+2
-2
@@ -359,7 +359,7 @@ 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:**
|
||||
|
||||
@@ -372,7 +372,7 @@ See [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md) for common issues and sol
|
||||
- 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
|
||||
|
||||
|
||||
@@ -33,7 +33,8 @@
|
||||
<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="#api">API</a> •
|
||||
<a href="docs/content/docs/overview/troubleshooting.mdx">Troubleshooting</a>
|
||||
</p>
|
||||
|
||||
<br/>
|
||||
@@ -91,6 +92,8 @@ Voicebox is a **local-first voice cloning studio** — a free and open-source al
|
||||
|
||||
> **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
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
},
|
||||
"app": {
|
||||
"name": "@voicebox/app",
|
||||
"version": "0.2.0",
|
||||
"version": "0.4.1",
|
||||
"dependencies": {
|
||||
"@dnd-kit/core": "^6.3.1",
|
||||
"@dnd-kit/sortable": "^10.0.0",
|
||||
@@ -72,9 +72,10 @@
|
||||
},
|
||||
"landing": {
|
||||
"name": "@voicebox/landing",
|
||||
"version": "0.2.0",
|
||||
"version": "0.4.1",
|
||||
"dependencies": {
|
||||
"@fontsource/space-grotesk": "^5.2.10",
|
||||
"@icons-pack/react-simple-icons": "^13.13.0",
|
||||
"@radix-ui/react-separator": "^1.1.8",
|
||||
"@radix-ui/react-slot": "^1.2.4",
|
||||
"autoprefixer": "^10.4.17",
|
||||
@@ -100,7 +101,7 @@
|
||||
},
|
||||
"tauri": {
|
||||
"name": "@voicebox/tauri",
|
||||
"version": "0.2.0",
|
||||
"version": "0.4.1",
|
||||
"dependencies": {
|
||||
"@tauri-apps/api": "^2.0.0",
|
||||
"@tauri-apps/plugin-dialog": "^2.0.0",
|
||||
@@ -123,7 +124,7 @@
|
||||
},
|
||||
"web": {
|
||||
"name": "@voicebox/web",
|
||||
"version": "0.2.0",
|
||||
"version": "0.4.1",
|
||||
"dependencies": {
|
||||
"@tanstack/react-query": "^5.0.0",
|
||||
"react": "^18.3.0",
|
||||
@@ -287,6 +288,8 @@
|
||||
|
||||
"@humanwhocodes/object-schema": ["@humanwhocodes/[email protected]", "", {}, "sha512-93zYdMES/c1D69yZiKDBj0V24vqNzB/koF26KPaagAfd3P/4gUlh3Dys5ogAK+Exi9QyzlD8x/08Zt7wIKcDcA=="],
|
||||
|
||||
"@icons-pack/react-simple-icons": ["@icons-pack/[email protected]", "", { "peerDependencies": { "react": "^16.13 || ^17 || ^18 || ^19" } }, "sha512-B5HhQMIpcSH4z8IZ8HFhD59CboHceKYMpPC9kAwGyKntvPdyJJv26DLu4Z1wAjcCLyrJhf11tMhiQGom9Rxb9g=="],
|
||||
|
||||
"@img/colour": ["@img/[email protected]", "", {}, "sha512-A5P/LfWGFSl6nsckYtjw9da+19jB8hkJ6ACTGcDfEJ0aE+l2n2El7dsVM7UVHZQ9s2lmYMWlrS21YLy2IR1LUw=="],
|
||||
|
||||
"@img/sharp-darwin-arm64": ["@img/[email protected]", "", { "optionalDependencies": { "@img/sharp-libvips-darwin-arm64": "1.2.4" }, "os": "darwin", "cpu": "arm64" }, "sha512-imtQ3WMJXbMY4fxb/Ndp6HBTNVtWCUI0WdobyheGf5+ad6xX8VIDO8u2xE4qc/fr08CKG/7dDseFtn6M6g/r3w=="],
|
||||
|
||||
+44
-10
@@ -1,6 +1,6 @@
|
||||
# Voicebox Project Status & Roadmap
|
||||
|
||||
> Last updated: 2026-04-18 | Current version: **v0.4.1** | ~155 open issues | 12 open PRs
|
||||
> Last updated: 2026-04-18 | Current version: **v0.4.1** | 232 open issues | 12 open PRs
|
||||
|
||||
---
|
||||
|
||||
@@ -224,6 +224,8 @@ POST /generate
|
||||
- **Blackwell (RTX 50-series) CUDA**: cu128 + sm_120 kernel support shipped (PR #401, #316), but users still report `cudaErrorNoKernelImageForDevice` (#417, #400, #396, #395, #390, #362) — likely a stale CUDA binary on upgraded installs. Needs a follow-up diagnostic / forced re-download path.
|
||||
- **Long text 50k character limit** (#464, #365, #354): Still hit on GPU despite chunking (PR #266). Chunking reliability needs another pass.
|
||||
- **ROCm on RDNA 3/4** (#469): `HSA_OVERRIDE_GFX_VERSION` is hardcoded and harms newer cards.
|
||||
- **`flash-attn is not installed` warning on every platform (cosmetic, common user complaint)**: Our transformer-based engines (Chatterbox / Qwen) emit `Warning: flash-attn is not installed. Will only run the manual PyTorch version. Please install flash-attn for faster inference.` on every startup, on every platform — we don't pin `flash-attn` in requirements because installing it is fragile and version-sensitive. Fallback is PyTorch SDPA, which is near-FA2 throughput on Ampere+ and is what actually runs. **Per-platform reality:** (a) **macOS/Apple Silicon** — FlashAttention is CUDA-only, irrelevant here; MLX has its own attention kernels. (b) **Linux** — `pip install flash-attn --no-build-isolation` works but takes 20+ min to compile. (c) **Windows** — no official support (Dao-AILab README still says only "Might work"; source builds routinely fail on recent CUDA/MSVC, issues #1715, #1828, #2395). Windows users can install community prebuilt wheels from `kingbri1/flash-attention` or `bdashore3/flash-attention` (latest v2.8.3, Aug 2025; `win_amd64` wheels for CUDA 12.4/12.8, Torch 2.6–2.9, Python 3.10–3.13) matching their exact CUDA/Torch/Python, or use WSL2. **Native-Windows alternatives worth considering as a build-time swap:** SageAttention (thu-ml, Apache 2.0, claims 2–5× over FA2) and xformers (official Windows wheels). **Action for us:** troubleshooting doc now covers it (see `docs/content/docs/overview/troubleshooting.mdx`), and we should optionally suppress the warning via `logging.getLogger(...).setLevel(ERROR)` at backend import since the fallback is functionally fine.
|
||||
- **WebAudio playback dies after audio-session interruption** (#41, plus an internal repro where the app is backgrounded long enough): WaveSurfer's `AudioContext` gets suspended by macOS — either because another app grabs the audio output, or because the WKWebView throttles when backgrounded. `play()` resolves and `timeupdate` can still fire, but no audio reaches the output. Only app restart fixes it. **Things already tried that didn't work:** (a) swapping WaveSurfer backend away from WebAudio — introduced more bugs, not an option; (b) remount hook on the player — doesn't help because a freshly-created `AudioContext` is born suspended and only resumes on a user gesture. PR #293 was a prior partial fix that doesn't cover this path. **Next thing to try** (not yet attempted — confirmed via grep of `AudioPlayer.tsx`): call `wavesurfer.getMediaElement().getGainNode().context.resume()` on the play button click (the click itself is a valid user gesture), plus a `visibilitychange` + `statechange` listener as belt-and-suspenders. The `ctx.resume()` pattern already exists in the codebase at `useStoryPlayback.ts:52` — just not wired into the main player.
|
||||
|
||||
---
|
||||
|
||||
@@ -303,9 +305,15 @@ POST /generate
|
||||
|
||||
Still reported. Users get stuck downloads, can't resume, offline mode edge cases.
|
||||
|
||||
**Key issues:** #475 (MAC CustomVoice install error), #449 (infinite loading macOS), #445 (can't download CustomVoice), #462 (Qwen requires internet even when loaded — regression from #150), #434 (infinite retry loop offline — PR #443 open), #432 (storage location change hangs when empty — partly fixed by PR #439/#433), #181, #180.
|
||||
**Key issues:** #475 (MAC CustomVoice install error), #449 (infinite loading macOS), #445 (can't download CustomVoice), #462 (Qwen requires internet even when loaded — regression from #150), #434 (infinite retry loop offline — PR #443 open), #432 (storage location change hangs when empty — partly fixed by PR #439/#433), #348 (TADA 3B Multilingual download fails), #336 (TADA model not listed in app), #275 (`No module named 'chatterbox'` on download), #304 (whisper-base feature extractor load error), #287 (macOS ARM `check_model_inputs` ImportError on new version), #181, #180.
|
||||
|
||||
**Fix path:** PR #443 addresses infinite offline retry. CustomVoice-specific download failures (#475, #445) need triage — likely related to frozen-binary import fixes in PR #438.
|
||||
**Fix path:** PR #443 addresses infinite offline retry. CustomVoice-specific download failures (#475, #445) need triage — likely related to frozen-binary import fixes in PR #438. TADA cluster (#336, #348) and macOS ARM import regressions (#287, #275, #304) need a dedicated triage pass.
|
||||
|
||||
**Qwen 0.6B-downloads-1.7B reports:** **#485** (2026-04-19), **#423** (macOS M1), **#329**. Platform-dependent:
|
||||
|
||||
- **On MLX (Apple Silicon) — not a bug.** `mlx-community` only publishes 1.7B-Base-bf16 weights, so the 0.6B Base option intentionally resolves to the same repo (`backend/backends/__init__.py:180` — `# 0.6B not available in MLX, falls back`). UX gap: the selector offers a size that doesn't exist on the active backend. Fix: (a) hide the 0.6B option on MLX, or (b) label it "0.6B (uses 1.7B on Apple Silicon)".
|
||||
- **On PyTorch (Windows/Linux/CUDA/ROCm/XPU/CPU) — real bug if reported.** Both 0.6B and 1.7B have distinct repos (`Qwen/Qwen3-TTS-12Hz-0.6B-Base` vs `-1.7B-Base`). Triage each report by platform before merging into the MLX cluster.
|
||||
- **Qwen CustomVoice (either platform)** — no fallback, both sizes always have dedicated repos.
|
||||
|
||||
### Language Requests (ongoing)
|
||||
|
||||
@@ -364,6 +372,9 @@ Notable:
|
||||
- **#383** — Concatenate partial reference audio into generated audio
|
||||
- **#382** — Lightning.ai support
|
||||
- **#376** — Remote mode
|
||||
- **#353** — Audio transcoding
|
||||
- **#317** — Voice pitch control
|
||||
- **#189** — "Auto" language option
|
||||
- **#173** — Vocal intonation/inflection control
|
||||
- **#165, #270** — Audiobook mode (PR #154 open)
|
||||
- **#242** — Seed value pinning
|
||||
@@ -371,17 +382,40 @@ Notable:
|
||||
- **#235** — Finetuned Qwen3-TTS tokenizer (PR #253 open)
|
||||
- **#144** — Copy text to clipboard
|
||||
|
||||
### Housekeeping / Triage Needed
|
||||
|
||||
| Issue | Reason |
|
||||
|-------|--------|
|
||||
| **#431**, **#408** | Spam — Chinese "free Claude API" promos. Close. |
|
||||
| **#398** ("Excelente") | Non-issue. Close. |
|
||||
| **#357** | Informational — project featured in Awesome MLX. Close after acknowledgement. |
|
||||
| **#374**, **#377** | Version-release questions, no bug. Close. |
|
||||
| **#306** ("voice model"), **#389** ("New model"), **#473** ("New functionality") | Title-only issues, no content. Request details or close. |
|
||||
| **#309** | Uninstall/cleanup question. Answer and close. |
|
||||
| **#241** | "How to use in Colab" — support question, not a bug. |
|
||||
| **#423** / **#485** / **#329** | Platform-dependent. On MLX: not a bug (0.6B weights don't exist upstream, fallback is intentional — fix UX). On PyTorch: real bug if reproducible. Classify each by reporter's platform before deduping. |
|
||||
| **#336** / **#348** | TADA download/registration cluster — triage together. |
|
||||
| **#287** / **#275** / **#304** | macOS ARM import regressions on new version — likely one root cause. |
|
||||
| **#292**, **#349** | Possibly already fixed by merged PRs (#321/#412 and #345). Verify + close. |
|
||||
|
||||
**~70 older issues (pre-#170) not individually categorized above.** Most are long-tail support questions or duplicates of problems now addressed by the multi-engine / model-registry work. A dedicated backlog-sweep pass is overdue.
|
||||
|
||||
### Bugs (ongoing)
|
||||
|
||||
| Category | Issues |
|
||||
|----------|--------|
|
||||
| Generation failures | #476, #467, #452, #459 (voice clone fetch error), #468 (tada-1b marked error), #437, #282 |
|
||||
| Audio quality | #456 (clipping errors v0.4.0), #436 (emotion labels), #333 (pitch/echo), #307 (by-model breakdown) |
|
||||
| File ops | #477 (spacy_pkuseg dict missing on frozen Windows build), #472 (storage location change) |
|
||||
| Windows | #466 (install problem), #273 (port 8000 conflict) |
|
||||
| Linux | #471 (thread-safe PULSE_SOURCE), #413 (Arch build), #409 (Kubuntu build), #341 |
|
||||
| macOS | #441 (older macOS), #369 (malware flag), #171 (ARM64 binary won't open) |
|
||||
| Profile/UI | #360 (Kokoro profile hides others — partly addressed by auto-switch), #299 (drag-drop on Win11), #329 (size selector state bug) |
|
||||
| Generation failures | #476, #467, #452, #459 (voice clone fetch error), #468 (tada-1b marked error), #437, #300, #301, #282 |
|
||||
| Audio quality | #456 (clipping errors v0.4.0), #436 (emotion labels), #333 (pitch/echo), #307 (by-model breakdown), #340 (all generations say "www...") |
|
||||
| Transcription | #371 (fails every time), #291 (extract transcription from generated audio) |
|
||||
| Effects / presets | #349 ("Failed to save" when creating effects presets — possibly fixed by merged #345) |
|
||||
| File ops | #477 (spacy_pkuseg dict missing on frozen Windows build), #472 (storage location change), #283 (allow longer files for voice creation + in-app trim), #350 (failed to add sample) |
|
||||
| History | #292 (can't delete failed generations — possibly fixed by merged #321/#412) |
|
||||
| Windows | #466 (install problem), #375 (WinError 5 access denied), #273 (port 8000 conflict), #201 (model doesn't stay loaded) |
|
||||
| Linux | #471 (thread-safe PULSE_SOURCE), #413 (Arch build), #409 (Kubuntu build), #351, #341 |
|
||||
| macOS | #441 (older macOS), #369 (malware flag), #334 (microphone permission), #287 (`check_model_inputs` ImportError — regression), #171 (ARM64 binary won't open) |
|
||||
| Profile/UI | #360 (Kokoro profile hides others — partly addressed by auto-switch), #299 (drag-drop on Win11), #329 (size selector state bug), #393 (stuck loading screen after reinstall to new dir) |
|
||||
| Integrations | #397 (SAMMI-bot 422 Unprocessable Entity) |
|
||||
| Audio playback / session | **#41** (macOS: Voicebox goes silent after another app takes audio output; restart restores it) — see deep-dive below |
|
||||
| Database | #174 (sqlite3 IntegrityError) |
|
||||
|
||||
---
|
||||
|
||||
@@ -1,311 +0,0 @@
|
||||
---
|
||||
title: "Troubleshooting Guide"
|
||||
description: "Common issues and solutions for Voicebox"
|
||||
---
|
||||
|
||||
Common issues and solutions for Voicebox.
|
||||
|
||||
## Installation Issues
|
||||
|
||||
### macOS: "Voicebox cannot be opened because it is from an unidentified developer"
|
||||
|
||||
**Solution:**
|
||||
1. Right-click the `.dmg` file
|
||||
2. Select "Open"
|
||||
3. Click "Open" in the security dialog
|
||||
4. Alternatively, go to System Settings → Privacy & Security → Allow Voicebox
|
||||
|
||||
### Windows: "Windows protected your PC"
|
||||
|
||||
**Solution:**
|
||||
1. Click "More info"
|
||||
2. Click "Run anyway"
|
||||
3. Windows Defender may flag new software; this is normal for unsigned apps
|
||||
|
||||
### Linux: AppImage won't run
|
||||
|
||||
**Solution:**
|
||||
```bash
|
||||
chmod +x voicebox-*.AppImage
|
||||
./voicebox-*.AppImage
|
||||
```
|
||||
|
||||
## Runtime Issues
|
||||
|
||||
### Server won't start
|
||||
|
||||
**Symptoms:** App opens but shows "Server not connected"
|
||||
|
||||
**Solutions:**
|
||||
1. **Check Python installation**
|
||||
```bash
|
||||
python --version # Should be 3.11+
|
||||
```
|
||||
|
||||
2. **Check server binary exists**
|
||||
- Look in `tauri/src-tauri/binaries/` for your platform
|
||||
- Binary should match your system architecture
|
||||
|
||||
3. **Check permissions**
|
||||
```bash
|
||||
# macOS/Linux
|
||||
chmod +x tauri/src-tauri/binaries/voicebox-server-*
|
||||
```
|
||||
|
||||
4. **Check logs**
|
||||
- macOS: Open Console.app and search for "voicebox"
|
||||
- Linux: Check `~/.local/share/voicebox/` for logs
|
||||
- Windows: Check Event Viewer
|
||||
|
||||
### "Model download failed"
|
||||
|
||||
**Symptoms:** First generation fails with download error
|
||||
|
||||
**Solutions:**
|
||||
1. **Check internet connection**
|
||||
- Models download from HuggingFace Hub (~2-4GB)
|
||||
- First download may take several minutes
|
||||
|
||||
2. **Check disk space**
|
||||
- Models are cached in `~/.cache/huggingface/`
|
||||
- Ensure at least 5GB free space
|
||||
|
||||
3. **Manual download** (if automatic fails)
|
||||
```bash
|
||||
pip install huggingface_hub
|
||||
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base
|
||||
```
|
||||
|
||||
### "Out of memory" errors
|
||||
|
||||
**Symptoms:** Generation fails with CUDA/VRAM errors
|
||||
|
||||
**Solutions:**
|
||||
1. **Use smaller model**
|
||||
- Switch to 0.6B model instead of 1.7B
|
||||
- Settings → Model Management → Load 0.6B
|
||||
|
||||
2. **Close other applications**
|
||||
- Free up GPU memory
|
||||
- Close browser tabs, other ML apps
|
||||
|
||||
3. **Use CPU mode**
|
||||
- Slower but works without GPU
|
||||
- Backend automatically falls back to CPU
|
||||
|
||||
### MLX "Failed to load the default metallib" error (Apple Silicon)
|
||||
|
||||
**Symptoms:** Generation fails with "library not found" or "metallib" errors
|
||||
|
||||
**Solutions:**
|
||||
1. **Rebuild server binary**
|
||||
```bash
|
||||
just build-server
|
||||
```
|
||||
The build script automatically includes MLX Metal shader libraries on Apple Silicon.
|
||||
|
||||
2. **Check MLX installation**
|
||||
```bash
|
||||
pip install -r backend/requirements-mlx.txt
|
||||
```
|
||||
|
||||
3. **Verify backend detection**
|
||||
- Check server logs for "Backend: MLX"
|
||||
- If showing "Backend: PYTORCH", MLX may not be installed correctly
|
||||
|
||||
### Audio playback issues
|
||||
|
||||
**Symptoms:** Generated audio won't play
|
||||
|
||||
**Solutions:**
|
||||
1. **Check audio format**
|
||||
- Audio is saved as WAV files
|
||||
- Ensure your system supports WAV playback
|
||||
|
||||
2. **Try downloading audio**
|
||||
- Right-click → Download
|
||||
- Play in external player
|
||||
|
||||
3. **Check browser permissions** (web version)
|
||||
- Allow audio autoplay in browser settings
|
||||
|
||||
### Slow generation
|
||||
|
||||
**Symptoms:** Generation takes >30 seconds
|
||||
|
||||
**Solutions:**
|
||||
1. **Check backend type** (Apple Silicon)
|
||||
- Check Settings → Server Status
|
||||
- Should show "Backend: MLX" on Apple Silicon
|
||||
- If showing "Backend: PYTORCH", install MLX: `pip install -r backend/requirements-mlx.txt`
|
||||
- MLX provides 4-5x faster inference on Apple Silicon
|
||||
|
||||
2. **Use GPU** (if available)
|
||||
- Check Settings → Server Status
|
||||
- Should show "GPU available: true"
|
||||
- Apple Silicon: Should show "Metal (Apple Silicon via MLX)"
|
||||
- Windows/Linux: Should show "CUDA" if GPU available
|
||||
|
||||
3. **Enable caching**
|
||||
- Voice prompts are cached automatically
|
||||
- Second generation with same voice should be faster
|
||||
|
||||
4. **Use smaller model**
|
||||
- 0.6B model is faster than 1.7B
|
||||
- Quality difference is minimal for most voices
|
||||
|
||||
5. **Check system resources**
|
||||
- Close other CPU/GPU intensive apps
|
||||
- Ensure adequate RAM (8GB+ recommended)
|
||||
|
||||
## API Issues
|
||||
|
||||
### "Connection refused" when using API
|
||||
|
||||
**Solutions:**
|
||||
1. **Check server is running**
|
||||
```bash
|
||||
curl http://localhost:17493/health
|
||||
```
|
||||
|
||||
2. **Check remote mode**
|
||||
- If connecting remotely, ensure server is started with `--host 0.0.0.0`
|
||||
- Check firewall settings
|
||||
|
||||
3. **Check port availability**
|
||||
- The current local app and dev workflow uses port 17493 by default
|
||||
- Ensure no other service is using it
|
||||
|
||||
### CORS errors in browser
|
||||
|
||||
**Solutions:**
|
||||
1. **Use desktop app** (recommended)
|
||||
- Desktop app doesn't have CORS restrictions
|
||||
|
||||
2. **Configure CORS** (for web deployment)
|
||||
- Update `backend/main.py` CORS settings
|
||||
- Add your domain to allowed origins
|
||||
|
||||
## Update Issues
|
||||
|
||||
### "Update check failed"
|
||||
|
||||
**Solutions:**
|
||||
1. **Check internet connection**
|
||||
- Updates are fetched from GitHub releases
|
||||
|
||||
2. **Check GitHub access**
|
||||
- Ensure `github.com` is accessible
|
||||
- Check firewall/proxy settings
|
||||
|
||||
3. **Manual update**
|
||||
- Download latest release from GitHub
|
||||
- Install manually
|
||||
|
||||
### "Invalid signature" error
|
||||
|
||||
**Solutions:**
|
||||
1. **Re-download installer**
|
||||
- Signature may be corrupted
|
||||
- Download fresh copy from GitHub
|
||||
|
||||
2. **Check release integrity**
|
||||
- Verify `.sig` file matches installer
|
||||
- Report issue if signature is invalid
|
||||
|
||||
## Data Issues
|
||||
|
||||
### Profiles disappeared
|
||||
|
||||
**Solutions:**
|
||||
1. **Check data directory**
|
||||
- macOS: `~/Library/Application Support/sh.voicebox.app/`
|
||||
- Windows: `%APPDATA%/sh.voicebox.app/`
|
||||
- Linux: `~/.config/sh.voicebox.app/`
|
||||
|
||||
2. **Check database**
|
||||
- Database: `data/voicebox.db`
|
||||
- Ensure file exists and is readable
|
||||
|
||||
3. **Restore from backup**
|
||||
- Profiles can be exported/imported
|
||||
- Check for backup files
|
||||
|
||||
### "Database locked" error
|
||||
|
||||
**Solutions:**
|
||||
1. **Close other instances**
|
||||
- Ensure only one Voicebox instance is running
|
||||
|
||||
2. **Restart app**
|
||||
- Close and reopen Voicebox
|
||||
|
||||
3. **Check file permissions**
|
||||
- Ensure database file is writable
|
||||
- Check directory permissions
|
||||
|
||||
## Development Issues
|
||||
|
||||
### Build fails
|
||||
|
||||
**Solutions:**
|
||||
1. **Check Rust installation**
|
||||
```bash
|
||||
rustc --version
|
||||
rustup update
|
||||
```
|
||||
|
||||
2. **Check Tauri dependencies**
|
||||
```bash
|
||||
cd tauri
|
||||
bun install
|
||||
```
|
||||
|
||||
3. **Clean build**
|
||||
```bash
|
||||
cd tauri/src-tauri
|
||||
cargo clean
|
||||
cd ../..
|
||||
just build
|
||||
```
|
||||
|
||||
### API client generation fails
|
||||
|
||||
**Solutions:**
|
||||
1. **Start backend server**
|
||||
```bash
|
||||
just dev-backend
|
||||
```
|
||||
|
||||
2. **Check OpenAPI endpoint**
|
||||
```bash
|
||||
curl http://localhost:17493/openapi.json
|
||||
```
|
||||
|
||||
3. **Regenerate client**
|
||||
```bash
|
||||
just generate-api
|
||||
```
|
||||
|
||||
## Still Having Issues?
|
||||
|
||||
1. **Check existing issues**
|
||||
- Search GitHub issues for similar problems
|
||||
- Check closed issues for solutions
|
||||
|
||||
2. **Create new issue**
|
||||
- Include:
|
||||
- OS and version
|
||||
- Voicebox version
|
||||
- Steps to reproduce
|
||||
- Error messages/logs
|
||||
- Screenshots (if applicable)
|
||||
|
||||
3. **Get help**
|
||||
- Check documentation in `docs/`
|
||||
- Review `backend/README.md` for API details
|
||||
- See `CONTRIBUTING.md` for development help
|
||||
|
||||
---
|
||||
|
||||
For more help, open an issue on [GitHub](https://github.com/jamiepine/voicebox/issues).
|
||||
@@ -29,6 +29,14 @@ Windows SmartScreen may warn that the app is unrecognized.
|
||||
This is expected for unsigned applications. We're working on code signing for future releases.
|
||||
</Callout>
|
||||
|
||||
### Linux: AppImage Won't Run
|
||||
|
||||
**Solution:**
|
||||
```bash
|
||||
chmod +x voicebox-*.AppImage
|
||||
./voicebox-*.AppImage
|
||||
```
|
||||
|
||||
## Server Issues
|
||||
|
||||
### Backend Server Won't Start
|
||||
@@ -85,6 +93,52 @@ Windows SmartScreen may warn that the app is unrecognized.
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
### `flash-attn is not installed` Warning in Server Logs
|
||||
|
||||
**Symptoms:**
|
||||
```
|
||||
Warning: flash-attn is not installed. Will only run the manual PyTorch version.
|
||||
Please install flash-attn for faster inference.
|
||||
```
|
||||
|
||||
**This is harmless.** The warning is emitted by our transformer-based engines (Chatterbox / Qwen) on every startup. FlashAttention is an optional acceleration library — when it's not present, PyTorch's built-in scaled-dot-product attention (SDPA) runs instead, which is near-FA2 throughput on modern GPUs. Generation works normally.
|
||||
|
||||
**Why it shows up on every platform:**
|
||||
- **Windows:** `flash-attn` has no official Windows support. The upstream project (Dao-AILab/flash-attention) still only says it *might* work, and source builds typically fail on recent CUDA/MSVC combinations.
|
||||
- **macOS (Apple Silicon):** FlashAttention is CUDA-only and doesn't apply here at all. MLX has its own optimized attention kernels.
|
||||
- **Linux:** It's not pinned in our requirements because installing it is fragile and version-sensitive; users who want it install it themselves.
|
||||
|
||||
**Solutions (all optional):**
|
||||
|
||||
<AccordionGroup>
|
||||
<Accordion title="Ignore it (recommended)">
|
||||
PyTorch SDPA is what actually runs the model, and on Ampere/Ada/Hopper GPUs it's within a few percent of FA2 for our workloads. You won't notice a meaningful speed difference.
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Install flash-attn on Linux">
|
||||
```bash
|
||||
pip install flash-attn --no-build-isolation
|
||||
```
|
||||
|
||||
Requires a matching CUDA toolkit. Build can take 20+ minutes.
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Install flash-attn on Windows (community wheels)">
|
||||
Official builds don't exist, but community maintainers publish prebuilt wheels:
|
||||
|
||||
- [kingbri1/flash-attention releases](https://github.com/kingbri1/flash-attention/releases)
|
||||
- [bdashore3/flash-attention releases](https://github.com/bdashore3/flash-attention/releases)
|
||||
|
||||
Pick the wheel matching your exact CUDA + PyTorch + Python combination. Example:
|
||||
|
||||
```bash
|
||||
pip install https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.8.0cxx11abiFALSE-cp312-cp312-win_amd64.whl
|
||||
```
|
||||
|
||||
Alternatively, run Voicebox's backend inside WSL2 and use the standard Linux wheels.
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
### Connection Timeout
|
||||
|
||||
**Symptoms:**
|
||||
@@ -174,6 +228,34 @@ This is expected behavior. The first generation downloads the selected TTS engin
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
### MLX "Failed to load the default metallib" (Apple Silicon)
|
||||
|
||||
**Symptoms:**
|
||||
- Generation fails with "library not found" or "metallib" errors
|
||||
- Server logs reference missing Metal shader libraries
|
||||
|
||||
**Solutions:**
|
||||
|
||||
<AccordionGroup>
|
||||
<Accordion title="Rebuild the Server Binary">
|
||||
```bash
|
||||
just build-server
|
||||
```
|
||||
|
||||
The build script bundles MLX Metal shader libraries on Apple Silicon automatically.
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Reinstall MLX Dependencies">
|
||||
```bash
|
||||
pip install -r backend/requirements-mlx.txt
|
||||
```
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Verify Backend Detection">
|
||||
Check Settings → Server Status. Should show **Backend: MLX** on Apple Silicon. If it shows **Backend: PYTORCH**, MLX isn't installed correctly.
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
## Audio Issues
|
||||
|
||||
### No Audio Playback
|
||||
@@ -357,7 +439,26 @@ Restart the app to create a fresh database.
|
||||
- Check your internet connection
|
||||
- Check HuggingFace Hub status
|
||||
- Try using a VPN if HuggingFace is blocked in your region
|
||||
- Manually download and place in cache directory
|
||||
- Manually download via the HuggingFace CLI and place in the cache directory:
|
||||
|
||||
```bash
|
||||
pip install huggingface_hub
|
||||
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base
|
||||
```
|
||||
|
||||
### Qwen 0.6B Downloads the Same Files as 1.7B on Apple Silicon
|
||||
|
||||
**Symptoms:**
|
||||
- You select Qwen 0.6B on an Apple Silicon Mac and the download is the same size as 1.7B
|
||||
- Generation speed and VRAM usage match 1.7B, not the expected smaller model
|
||||
|
||||
**Explanation:**
|
||||
This is intentional, not a bug. The MLX community only publishes `mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16` — there is no 0.6B MLX build. Voicebox's model registry falls back to the 1.7B weights when 0.6B is selected on MLX (see `backend/backends/__init__.py`).
|
||||
|
||||
**Solution:**
|
||||
- On Apple Silicon, both size options use the 1.7B model — pick either.
|
||||
- If you specifically need a smaller model, switch to **Kokoro 82M** (~350 MB) or **LuxTTS** (~300 MB) — both CPU-realtime.
|
||||
- On Windows/Linux with PyTorch, 0.6B and 1.7B are distinct repos and behave differently.
|
||||
|
||||
### Wrong Model Version
|
||||
|
||||
@@ -404,6 +505,16 @@ rmdir /s %USERPROFILE%\.cache\huggingface\hub\models--Qwen*
|
||||
<Accordion title="Update GPU Drivers">
|
||||
Outdated drivers can cause performance issues. Update to the latest NVIDIA drivers.
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Apple Silicon: Confirm MLX Backend">
|
||||
Check Settings → Server Status. Should show **Backend: MLX** on Apple Silicon — MLX is 4–5× faster than PyTorch here. If it shows **Backend: PYTORCH**, reinstall MLX:
|
||||
|
||||
```bash
|
||||
pip install -r backend/requirements-mlx.txt
|
||||
```
|
||||
|
||||
GPU availability should read "Metal (Apple Silicon via MLX)".
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
### High Memory Usage
|
||||
@@ -417,6 +528,21 @@ rmdir /s %USERPROFILE%\.cache\huggingface\hub\models--Qwen*
|
||||
- Clear generation history
|
||||
- Restart the app periodically
|
||||
|
||||
## Update Issues
|
||||
|
||||
### "Update Check Failed"
|
||||
|
||||
**Solutions:**
|
||||
- Confirm your internet connection — updates are fetched from GitHub releases.
|
||||
- Ensure `github.com` is accessible and not blocked by a firewall or proxy.
|
||||
- As a fallback, download the latest release from GitHub and install manually.
|
||||
|
||||
### "Invalid Signature" Error
|
||||
|
||||
**Solutions:**
|
||||
- Re-download the installer — the signature may have been corrupted in transit.
|
||||
- Verify the `.sig` file matches the installer; if it doesn't, file an issue.
|
||||
|
||||
## Remote Mode Issues
|
||||
|
||||
### Can't Connect to Remote Server
|
||||
@@ -482,5 +608,3 @@ python --version
|
||||
# GPU info (if generation issues)
|
||||
nvidia-smi # NVIDIA GPUs
|
||||
```
|
||||
|
||||
For more detailed troubleshooting, see the [TROUBLESHOOTING.md](https://github.com/jamiepine/voicebox/blob/main/docs/TROUBLESHOOTING.md) file in the repository.
|
||||
|
||||
@@ -3,13 +3,14 @@
|
||||
"version": "0.4.1",
|
||||
"description": "Landing page for voicebox.sh",
|
||||
"scripts": {
|
||||
"dev": "bun --bun next dev --turbo",
|
||||
"dev": "next dev --turbo",
|
||||
"build": "bun --bun next build",
|
||||
"start": "bun --bun next start",
|
||||
"lint": "next lint"
|
||||
},
|
||||
"dependencies": {
|
||||
"@fontsource/space-grotesk": "^5.2.10",
|
||||
"@icons-pack/react-simple-icons": "^13.13.0",
|
||||
"@radix-ui/react-separator": "^1.1.8",
|
||||
"@radix-ui/react-slot": "^1.2.4",
|
||||
"autoprefixer": "^10.4.17",
|
||||
|
||||
@@ -1,42 +1,31 @@
|
||||
import { type NextRequest, NextResponse } from 'next/server';
|
||||
import { getLatestRelease } from '@/lib/releases';
|
||||
|
||||
export const dynamic = 'force-dynamic';
|
||||
|
||||
const PLATFORM_MAP: Record<
|
||||
string,
|
||||
keyof Awaited<ReturnType<typeof getLatestRelease>>['downloadLinks']
|
||||
> = {
|
||||
// Pretty URLs from README / docs (e.g. /download/mac-arm) are kept for
|
||||
// compatibility, but we now always route through the /download page so users
|
||||
// see context + a donate prompt + resources while the download kicks off.
|
||||
// The page handles the actual file trigger itself — no more silent redirects
|
||||
// to GitHub or direct asset URLs.
|
||||
const PLATFORM_ALIAS: Record<string, string> = {
|
||||
'mac-arm': 'macArm',
|
||||
macArm: 'macArm',
|
||||
'mac-intel': 'macIntel',
|
||||
macIntel: 'macIntel',
|
||||
windows: 'windows',
|
||||
linux: 'linux',
|
||||
};
|
||||
|
||||
export async function GET(
|
||||
_request: NextRequest,
|
||||
request: NextRequest,
|
||||
{ params }: { params: Promise<{ platform: string }> },
|
||||
) {
|
||||
const { platform } = await params;
|
||||
const key = PLATFORM_MAP[platform];
|
||||
|
||||
if (!key) {
|
||||
return NextResponse.json(
|
||||
{ error: `Unknown platform: ${platform}. Use: ${Object.keys(PLATFORM_MAP).join(', ')}` },
|
||||
{ status: 404 },
|
||||
);
|
||||
}
|
||||
|
||||
try {
|
||||
const release = await getLatestRelease();
|
||||
const url = release.downloadLinks[key];
|
||||
|
||||
if (!url) {
|
||||
return NextResponse.json({ error: `No download available for ${platform}` }, { status: 404 });
|
||||
}
|
||||
|
||||
return NextResponse.redirect(url);
|
||||
} catch {
|
||||
return NextResponse.redirect(`https://github.com/jamiepine/voicebox/releases/latest`);
|
||||
// No prebuilt Linux binary yet — send straight to the build-from-source page.
|
||||
if (platform === 'linux') {
|
||||
return NextResponse.redirect(new URL('/linux-install', request.url), 307);
|
||||
}
|
||||
const normalized = PLATFORM_ALIAS[platform];
|
||||
const target = new URL('/download', request.url);
|
||||
if (normalized) target.searchParams.set('platform', normalized);
|
||||
return NextResponse.redirect(target, 307);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,313 @@
|
||||
'use client';
|
||||
|
||||
import {
|
||||
ArrowLeft,
|
||||
Bot,
|
||||
Coffee,
|
||||
Download as DownloadIcon,
|
||||
FileText,
|
||||
Github,
|
||||
} from 'lucide-react';
|
||||
import Image from 'next/image';
|
||||
import Link from 'next/link';
|
||||
import { useEffect, useMemo, useState } from 'react';
|
||||
import { AppleIcon, LinuxIcon, WindowsIcon } from '@/components/PlatformIcons';
|
||||
import { Button } from '@/components/ui/button';
|
||||
import { DONATE_URL, GITHUB_RELEASES_PAGE, GITHUB_REPO } from '@/lib/constants';
|
||||
import type { DownloadLinks } from '@/lib/releases';
|
||||
|
||||
type Platform = keyof DownloadLinks;
|
||||
|
||||
type PlatformMeta = {
|
||||
key: Platform;
|
||||
label: string;
|
||||
description: string;
|
||||
icon: React.ComponentType<{ className?: string }>;
|
||||
};
|
||||
|
||||
const PLATFORMS: PlatformMeta[] = [
|
||||
{ key: 'macArm', label: 'macOS', description: 'Apple Silicon', icon: AppleIcon },
|
||||
{ key: 'macIntel', label: 'macOS', description: 'Intel (x64)', icon: AppleIcon },
|
||||
{ key: 'windows', label: 'Windows', description: '64-bit (MSI)', icon: WindowsIcon },
|
||||
{ key: 'linux', label: 'Linux', description: 'Build from source', icon: LinuxIcon },
|
||||
];
|
||||
|
||||
function detectPlatform(): Platform | null {
|
||||
if (typeof navigator === 'undefined') return null;
|
||||
const ua = navigator.userAgent;
|
||||
if (/Windows/i.test(ua)) return 'windows';
|
||||
if (/Linux/i.test(ua) && !/Android/i.test(ua)) return 'linux';
|
||||
if (/Mac/i.test(ua)) {
|
||||
// Apple Silicon Safari reports "Intel" for compat; default to ARM since
|
||||
// M-series is the majority. Users can click the Intel button if needed.
|
||||
return 'macArm';
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function parseQueryPlatform(search: string): Platform | null {
|
||||
const params = new URLSearchParams(search);
|
||||
const raw = params.get('platform');
|
||||
if (!raw) return null;
|
||||
// Accept both camelCase and hyphenated forms (/download/mac-arm → ?platform=mac-arm).
|
||||
const normalized = raw
|
||||
.toLowerCase()
|
||||
.replace(/[-_\s]/g, '')
|
||||
.replace('macarm', 'macArm')
|
||||
.replace('macintel', 'macIntel');
|
||||
const valid: Platform[] = ['macArm', 'macIntel', 'windows', 'linux'];
|
||||
return (valid as string[]).includes(normalized) ? (normalized as Platform) : null;
|
||||
}
|
||||
|
||||
export default function DownloadPage() {
|
||||
const [links, setLinks] = useState<DownloadLinks | null>(null);
|
||||
const [linksError, setLinksError] = useState(false);
|
||||
const [platform, setPlatform] = useState<Platform | null>(null);
|
||||
const [triggered, setTriggered] = useState(false);
|
||||
|
||||
useEffect(() => {
|
||||
const fromQuery = parseQueryPlatform(window.location.search);
|
||||
const resolved = fromQuery ?? detectPlatform();
|
||||
// No prebuilt Linux binary yet — send Linux users to the build-from-source
|
||||
// instructions instead of sitting on /download trying to trigger a
|
||||
// download that doesn't exist.
|
||||
if (resolved === 'linux') {
|
||||
window.location.replace('/linux-install');
|
||||
return;
|
||||
}
|
||||
setPlatform(resolved);
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
let cancelled = false;
|
||||
fetch('/api/releases')
|
||||
.then((r) => {
|
||||
if (!r.ok) throw new Error(`releases ${r.status}`);
|
||||
return r.json();
|
||||
})
|
||||
.then((data) => {
|
||||
if (cancelled) return;
|
||||
if (data.downloadLinks) setLinks(data.downloadLinks as DownloadLinks);
|
||||
})
|
||||
.catch(() => {
|
||||
if (!cancelled) setLinksError(true);
|
||||
});
|
||||
return () => {
|
||||
cancelled = true;
|
||||
};
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
if (triggered || !links || !platform) return;
|
||||
const url = links[platform];
|
||||
if (!url) return;
|
||||
|
||||
const a = document.createElement('a');
|
||||
a.href = url;
|
||||
a.rel = 'noopener';
|
||||
a.style.display = 'none';
|
||||
document.body.appendChild(a);
|
||||
a.click();
|
||||
document.body.removeChild(a);
|
||||
setTriggered(true);
|
||||
}, [triggered, links, platform]);
|
||||
|
||||
const activeMeta = useMemo(
|
||||
() => PLATFORMS.find((p) => p.key === platform) ?? null,
|
||||
[platform],
|
||||
);
|
||||
|
||||
return (
|
||||
<div className="min-h-screen bg-background">
|
||||
{/* Minimal branded header */}
|
||||
<header className="border-b border-border/50">
|
||||
<div className="mx-auto flex max-w-5xl items-center justify-between px-6 py-4">
|
||||
<Link href="/" className="flex items-center gap-2.5">
|
||||
<Image
|
||||
src="/voicebox-logo-app.webp"
|
||||
alt="Voicebox"
|
||||
width={28}
|
||||
height={28}
|
||||
className="h-7 w-7"
|
||||
/>
|
||||
<span className="text-[15px] font-semibold text-foreground">Voicebox</span>
|
||||
</Link>
|
||||
<Link
|
||||
href="/"
|
||||
className="flex items-center gap-1.5 text-sm text-muted-foreground hover:text-foreground transition-colors"
|
||||
>
|
||||
<ArrowLeft className="h-3.5 w-3.5" />
|
||||
Back to voicebox.sh
|
||||
</Link>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<main className="mx-auto max-w-5xl px-6 py-16 md:py-24">
|
||||
{/* Hero */}
|
||||
<div className="flex flex-col md:flex-row md:items-center gap-10 md:gap-14">
|
||||
<Image
|
||||
src="/voicebox-logo-app.webp"
|
||||
alt="Voicebox"
|
||||
width={200}
|
||||
height={200}
|
||||
priority
|
||||
className="h-32 w-32 md:h-44 md:w-44 shrink-0 drop-shadow-2xl"
|
||||
/>
|
||||
<div className="flex-1 min-w-0 text-center md:text-left">
|
||||
{triggered ? (
|
||||
<>
|
||||
<h1 className="text-4xl md:text-5xl font-semibold tracking-tight text-foreground mb-4">
|
||||
Your download has started.
|
||||
</h1>
|
||||
<p className="text-lg text-muted-foreground">
|
||||
{activeMeta
|
||||
? `Downloading Voicebox for ${activeMeta.label} (${activeMeta.description}). Check your downloads folder.`
|
||||
: 'Check your downloads folder for Voicebox.'}
|
||||
</p>
|
||||
</>
|
||||
) : (
|
||||
<>
|
||||
<h1 className="text-4xl md:text-5xl font-semibold tracking-tight text-foreground mb-4">
|
||||
{linksError ? "We couldn't load the latest release." : 'Download Voicebox'}
|
||||
</h1>
|
||||
<p className="text-lg text-muted-foreground">
|
||||
{linksError
|
||||
? 'Our release server is temporarily unreachable. Please try again in a moment.'
|
||||
: 'Pick your platform to get started.'}
|
||||
</p>
|
||||
</>
|
||||
)}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* Platform buttons — always visible as a fallback */}
|
||||
{linksError ? (
|
||||
<div className="mt-12 rounded-xl border border-border bg-card/60 backdrop-blur-sm p-6 text-center">
|
||||
<p className="text-sm text-muted-foreground mb-4">
|
||||
If this keeps happening, you can{' '}
|
||||
<a
|
||||
href={`${GITHUB_RELEASES_PAGE}/latest`}
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="text-accent underline underline-offset-2 hover:text-accent/80"
|
||||
>
|
||||
browse releases on GitHub
|
||||
</a>
|
||||
{' '}and grab the build for your platform manually.
|
||||
</p>
|
||||
</div>
|
||||
) : (
|
||||
<div className="mt-12 rounded-xl border border-border bg-card/60 backdrop-blur-sm p-6">
|
||||
<h2 className="text-sm font-medium text-foreground mb-4">
|
||||
{triggered ? 'Download not working?' : 'Choose your platform'}
|
||||
</h2>
|
||||
<div className="grid grid-cols-1 sm:grid-cols-2 gap-3">
|
||||
{PLATFORMS.map((meta) => {
|
||||
const isLinux = meta.key === 'linux';
|
||||
const url = isLinux ? '/linux-install' : links?.[meta.key];
|
||||
const isActive = meta.key === platform;
|
||||
const disabled = !isLinux && !url;
|
||||
return (
|
||||
<a
|
||||
key={meta.key}
|
||||
href={url ?? '#'}
|
||||
{...(isLinux ? {} : { download: true })}
|
||||
aria-disabled={disabled}
|
||||
onClick={(e) => {
|
||||
if (disabled) e.preventDefault();
|
||||
}}
|
||||
className={`flex items-center rounded-xl border px-5 py-4 transition-all group ${
|
||||
isActive
|
||||
? 'border-accent/40 bg-accent/5 hover:border-accent/60'
|
||||
: 'border-border bg-card/40 hover:border-accent/30 hover:bg-card'
|
||||
} ${disabled ? 'opacity-50 cursor-not-allowed' : ''}`}
|
||||
>
|
||||
<meta.icon className="h-6 w-6 shrink-0 text-muted-foreground group-hover:text-foreground transition-colors" />
|
||||
<div className="ml-4 flex-1">
|
||||
<div className="text-sm font-medium text-foreground">{meta.label}</div>
|
||||
<div className="text-xs text-muted-foreground">{meta.description}</div>
|
||||
</div>
|
||||
<DownloadIcon className="h-4 w-4 text-muted-foreground/60 group-hover:text-accent transition-colors" />
|
||||
</a>
|
||||
);
|
||||
})}
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* Donate — prominent, heartfelt, post-click context */}
|
||||
<div className="mt-16 rounded-2xl border border-border bg-gradient-to-br from-card via-card/80 to-background backdrop-blur-sm p-8 md:p-10 overflow-hidden relative">
|
||||
<div className="absolute top-0 right-0 w-64 h-64 bg-[#FFDD00]/5 rounded-full blur-3xl -translate-y-1/2 translate-x-1/2 pointer-events-none" />
|
||||
<div className="relative">
|
||||
<div className="inline-flex items-center gap-2 rounded-full border border-[#FFDD00]/30 bg-[#FFDD00]/10 px-3 py-1 mb-4">
|
||||
<Coffee className="h-3 w-3 text-[#FFDD00]" />
|
||||
<span className="text-[11px] font-medium uppercase tracking-wider text-[#FFDD00]">
|
||||
Hi from the maintainer
|
||||
</span>
|
||||
</div>
|
||||
<h2 className="text-2xl md:text-3xl font-semibold tracking-tight text-foreground mb-4">
|
||||
Jamie here — Voicebox is a side project.
|
||||
</h2>
|
||||
<p className="text-muted-foreground leading-relaxed mb-6 max-w-2xl">
|
||||
I build and maintain Voicebox in my spare time. It's completely
|
||||
free, open source, runs entirely on your machine — no accounts, no
|
||||
cloud, no subscriptions, no upsells. If it saves you an ElevenLabs
|
||||
bill or just made your day, a coffee genuinely helps me keep
|
||||
shipping updates, adding new models, and fixing bugs. Every little
|
||||
bit keeps the lights on.
|
||||
</p>
|
||||
<Button asChild size="lg" className="bg-[#FFDD00]/10 border-[#FFDD00]/30 text-[#FFDD00] hover:bg-[#FFDD00]/20 hover:border-[#FFDD00]/50">
|
||||
<a href={DONATE_URL} target="_blank" rel="noopener noreferrer">
|
||||
<Coffee className="h-4 w-4 mr-2" />
|
||||
Buy me a coffee
|
||||
</a>
|
||||
</Button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* Resources */}
|
||||
<div className="mt-10">
|
||||
<h2 className="text-sm font-medium text-foreground mb-4">While you wait</h2>
|
||||
<div className="grid grid-cols-1 md:grid-cols-3 gap-4">
|
||||
<a
|
||||
href="https://docs.voicebox.sh"
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-5 hover:border-accent/30 hover:bg-card transition-all group"
|
||||
>
|
||||
<FileText className="h-5 w-5 text-accent mb-3" />
|
||||
<h3 className="text-sm font-medium text-foreground mb-1">Read the docs</h3>
|
||||
<p className="text-xs text-muted-foreground leading-relaxed">
|
||||
Get familiar with Voicebox — setup, voice cloning, the REST API.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
href="https://deepwiki.com/jamiepine/voicebox"
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-5 hover:border-accent/30 hover:bg-card transition-all group"
|
||||
>
|
||||
<Bot className="h-5 w-5 text-accent mb-3" />
|
||||
<h3 className="text-sm font-medium text-foreground mb-1">Got questions? Ask AI.</h3>
|
||||
<p className="text-xs text-muted-foreground leading-relaxed">
|
||||
DeepWiki is an AI that knows Voicebox inside-out. Ask anything.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
href={GITHUB_REPO}
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-5 hover:border-accent/30 hover:bg-card transition-all group"
|
||||
>
|
||||
<Github className="h-5 w-5 text-accent mb-3" />
|
||||
<h3 className="text-sm font-medium text-foreground mb-1">Source on GitHub</h3>
|
||||
<p className="text-xs text-muted-foreground leading-relaxed">
|
||||
Star the repo, file issues, or contribute a PR.
|
||||
</p>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</main>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -17,12 +17,9 @@ import {Navbar} from "@/components/Navbar";
|
||||
import {AppleIcon, LinuxIcon, WindowsIcon} from "@/components/PlatformIcons";
|
||||
import {TutorialsSection} from "@/components/TutorialsSection";
|
||||
import {VoiceCreator} from "@/components/VoiceCreator";
|
||||
import {DOWNLOAD_LINKS, GITHUB_REPO} from "@/lib/constants";
|
||||
import type {DownloadLinks} from "@/lib/releases";
|
||||
import {GITHUB_REPO} from "@/lib/constants";
|
||||
|
||||
export default function Home() {
|
||||
const [downloadLinks, setDownloadLinks] =
|
||||
useState<DownloadLinks>(DOWNLOAD_LINKS);
|
||||
const [version, setVersion] = useState<string | null>(null);
|
||||
const [totalDownloads, setTotalDownloads] = useState<number | null>(null);
|
||||
|
||||
@@ -33,7 +30,6 @@ export default function Home() {
|
||||
return res.json();
|
||||
})
|
||||
.then((data) => {
|
||||
if (data.downloadLinks) setDownloadLinks(data.downloadLinks);
|
||||
if (data.version) setVersion(data.version);
|
||||
if (data.totalDownloads != null) setTotalDownloads(data.totalDownloads);
|
||||
})
|
||||
@@ -92,7 +88,7 @@ export default function Home() {
|
||||
style={{animationDelay: "300ms"}}
|
||||
>
|
||||
<a
|
||||
href="#download"
|
||||
href="/download"
|
||||
className="rounded-full bg-accent px-8 py-3.5 text-sm font-semibold uppercase tracking-wider text-white shadow-[0_4px_20px_hsl(43_60%_50%/0.3),inset_0_2px_0_rgba(255,255,255,0.2),inset_0_-2px_0_rgba(0,0,0,0.1)] transition-all hover:bg-accent-faint active:shadow-[0_2px_10px_hsl(43_60%_50%/0.3),inset_0_4px_8px_rgba(0,0,0,0.3)]"
|
||||
>
|
||||
Download
|
||||
@@ -403,8 +399,7 @@ export default function Home() {
|
||||
<div className="grid grid-cols-1 sm:grid-cols-2 gap-3 max-w-2xl mx-auto">
|
||||
{/* macOS ARM */}
|
||||
<a
|
||||
href={downloadLinks.macArm}
|
||||
download
|
||||
href="/download?platform=macArm"
|
||||
className="flex items-center rounded-xl border border-border bg-card/60 backdrop-blur-sm px-5 py-4 transition-all hover:border-accent/30 hover:bg-card group"
|
||||
>
|
||||
<AppleIcon className="h-6 w-6 shrink-0 text-muted-foreground group-hover:text-foreground transition-colors" />
|
||||
@@ -418,8 +413,7 @@ export default function Home() {
|
||||
|
||||
{/* macOS Intel */}
|
||||
<a
|
||||
href={downloadLinks.macIntel}
|
||||
download
|
||||
href="/download?platform=macIntel"
|
||||
className="flex items-center rounded-xl border border-border bg-card/60 backdrop-blur-sm px-5 py-4 transition-all hover:border-accent/30 hover:bg-card group"
|
||||
>
|
||||
<AppleIcon className="h-6 w-6 shrink-0 text-muted-foreground group-hover:text-foreground transition-colors" />
|
||||
@@ -431,8 +425,7 @@ export default function Home() {
|
||||
|
||||
{/* Windows */}
|
||||
<a
|
||||
href={downloadLinks.windows}
|
||||
download
|
||||
href="/download?platform=windows"
|
||||
className="flex items-center rounded-xl border border-border bg-card/60 backdrop-blur-sm px-5 py-4 transition-all hover:border-accent/30 hover:bg-card group"
|
||||
>
|
||||
<WindowsIcon className="h-6 w-6 shrink-0 text-muted-foreground group-hover:text-foreground transition-colors" />
|
||||
|
||||
@@ -29,8 +29,8 @@ const CURL_SNIPPET = `curl -X POST http://127.0.0.1:17493/generate \\
|
||||
-H "Content-Type: application/json" \\
|
||||
-d '{
|
||||
"text": "Welcome to the game, player one.",
|
||||
"profile_id": "morgan-freeman",
|
||||
"engine": "qwen",
|
||||
"profile_id": "b3f1c2d4-5e6f-4a7b-8c9d-0e1f2a3b4c5d",
|
||||
"engine": "qwen_custom_voice",
|
||||
"instruct": "warm, slow, cinematic"
|
||||
}' \\
|
||||
--output line.wav`;
|
||||
|
||||
@@ -45,7 +45,7 @@ export function Footer() {
|
||||
</a>
|
||||
</li>
|
||||
<li>
|
||||
<a href="#download" className="hover:text-foreground transition-colors">
|
||||
<a href="/download" className="hover:text-foreground transition-colors">
|
||||
Download
|
||||
</a>
|
||||
</li>
|
||||
|
||||
@@ -66,7 +66,7 @@ export function Navbar() {
|
||||
API
|
||||
</a>
|
||||
<a
|
||||
href="#download"
|
||||
href="/download"
|
||||
className="rounded-md px-3 py-1.5 text-sm font-medium text-muted-foreground transition-colors hover:text-foreground"
|
||||
>
|
||||
Download
|
||||
|
||||
@@ -1,23 +1,29 @@
|
||||
import { SiApple, SiLinux } from '@icons-pack/react-simple-icons';
|
||||
|
||||
// Official brand icons via Simple Icons (apple/linux). Simple Icons drops
|
||||
// Microsoft's mark due to trademark policy, so the Windows 11 flag is
|
||||
// inlined from Microsoft's public brand guidance.
|
||||
|
||||
export function AppleIcon({ className }: { className?: string }) {
|
||||
return (
|
||||
<svg className={className} viewBox="0 0 24 24" fill="currentColor">
|
||||
<path d="M17.05 20.28c-.98.95-2.05.88-3.08.4-1.09-.5-2.08-.48-3.24 0-1.44.62-2.2.44-3.06-.4C2.79 15.25 3.51 7.59 9.05 7.31c1.35.07 2.29.74 3.08.8 1.18-.24 2.31-.93 3.57-.84 1.51.12 2.65.72 3.4 1.8-3.12 1.87-2.38 5.98.48 7.13-.57 1.5-1.31 2.99-2.54 4.09l.01-.01zM12.03 7.25c-.15-2.23 1.66-4.07 3.74-4.25.29 2.58-2.34 4.5-3.74 4.25z" />
|
||||
</svg>
|
||||
);
|
||||
return <SiApple className={className} color="currentColor" />;
|
||||
}
|
||||
|
||||
export function LinuxIcon({ className }: { className?: string }) {
|
||||
return <SiLinux className={className} color="currentColor" />;
|
||||
}
|
||||
|
||||
export function WindowsIcon({ className }: { className?: string }) {
|
||||
return (
|
||||
<svg className={className} viewBox="0 0 24 24" fill="currentColor">
|
||||
<path d="M3 12V6.75l6-1.32v6.48L3 12zm17-9v8.75l-10 .15V5.21L20 3zM3 13l6 .09v7.81l-6-1.15V13zm17 .25V22l-10-1.8v-7.15l10 .15z" />
|
||||
</svg>
|
||||
);
|
||||
}
|
||||
|
||||
export function LinuxIcon({ className }: { className?: string }) {
|
||||
return (
|
||||
<svg className={className} viewBox="0 0 24 24" fill="currentColor">
|
||||
<path d="M12.504 0c-.155 0-.315.008-.48.021-4.226.333-3.105 4.807-3.17 6.298-.076 1.092-.3 1.953-1.05 3.02-.885 1.051-2.127 2.75-2.716 4.521-.278.832-.41 1.684-.287 2.489a.424.424 0 00-.11.135c-.26.26-.195.69-.133 1.001.054.27.112.553.077.784-.12.794-.3 1.593-.3 2.406 0 .599.18 1.193.3 1.791.12.599.3 1.193.3 1.792 0 .812.18 1.611.3 2.405.035.23-.023.514-.077.783-.062.312-.127.742.133 1.002a.424.424 0 00.11.135c-.123.805.01 1.657.287 2.489.589 1.771 1.831 3.47 2.716 4.521.75 1.067 0.974 1.928 1.05 3.02.065 1.491-1.056 5.965 3.17 6.298.165.013.325.021.48.021.155 0 .315-.008.48-.021 4.226-.333 3.105-4.807 3.17-6.298.076-1.092.3-1.953 1.05-3.02.885-1.051 2.127-2.75 2.716-4.521.278-.832.41-1.684.287-2.489a.424.424 0 00.11-.135c.26-.26.195-.69.133-1.001-.054-.27-.112-.553-.077-.784.12-.794.3-1.593.3-2.406 0-.599-.18-1.193-.3-1.791-.12-.599-.3-1.193-.3-1.792 0-.812-.18-1.611-.3-2.405-.035-.23.023-.514.077-.783.062-.312.127-.742-.133-1.002a.424.424 0 00-.11-.135c.123-.805-.01-1.657-.287-2.489-.589-1.771-1.831-3.47-2.716-4.521-.75-1.067-.974-1.928-1.05-3.02-.065-1.491 1.056-5.965-3.17-6.298C12.819.008 12.659 0 12.504 0z" />
|
||||
<svg
|
||||
className={className}
|
||||
viewBox="0 0 24 24"
|
||||
fill="currentColor"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
role="img"
|
||||
aria-label="Windows"
|
||||
>
|
||||
<title>Windows</title>
|
||||
<path d="M0 3.449L9.75 2.1v9.451H0m10.949-9.602L24 0v11.4l-13.051.149M0 12.6h9.75v9.451L0 20.699M10.949 12.6H24V24l-12.9-1.801" />
|
||||
</svg>
|
||||
);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user