From a8968d40813db938ba514f2383b507eb64cd649c Mon Sep 17 00:00:00 2001 From: James Pine Date: Mon, 16 Mar 2026 04:09:50 -0700 Subject: [PATCH] rewrite docs introduction based on README content --- docs/content/docs/overview/introduction.mdx | 88 +++++++++++---------- 1 file changed, 47 insertions(+), 41 deletions(-) diff --git a/docs/content/docs/overview/introduction.mdx b/docs/content/docs/overview/introduction.mdx index 99569a73..134f1d71 100644 --- a/docs/content/docs/overview/introduction.mdx +++ b/docs/content/docs/overview/introduction.mdx @@ -1,58 +1,64 @@ --- title: "Introduction" -description: "Welcome to Voicebox - the open-source voice synthesis studio" +description: "Voicebox is a local-first voice cloning studio -- a free and open-source alternative to ElevenLabs." --- ## 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. +Voicebox is a **local-first voice cloning studio** -- a free and open-source alternative to ElevenLabs. Clone voices from a few seconds of audio, generate speech in 23 languages across 4 TTS engines, apply post-processing effects, and compose multi-voice projects with a timeline editor. - - Voicebox App Screenshot - +- **Complete privacy** -- models and voice data stay on your machine +- **4 TTS engines** -- Qwen3-TTS, LuxTTS, Chatterbox Multilingual, and Chatterbox Turbo +- **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 +- **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 +- **Runs everywhere** -- macOS (MLX/Metal), Windows (CUDA), Linux, AMD ROCm, Intel Arc, Docker -Unlike cloud services that lock your voice data behind subscriptions, Voicebox gives you: +## TTS Engines -- **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 -- **Native performance** — built with Tauri (Rust), not Electron +Four engines with different strengths, switchable per-generation: -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. +| Engine | Languages | Strengths | +|--------|-----------|-----------| +| **Qwen3-TTS** (0.6B / 1.7B) | 10 | High-quality multilingual cloning, delivery instructions | +| **LuxTTS** | English | Lightweight (~1GB VRAM), 48kHz output, 150x realtime on CPU | +| **Chatterbox Multilingual** | 23 | Broadest language coverage | +| **Chatterbox Turbo** | English | Fast 350M model with paralinguistic emotion/sound tags | -## Key Features +## GPU Support - - - Instant cloning from just a few seconds of audio with Qwen3-TTS - - - Multi-track timeline for creating conversations and narratives - - - REST API for integrating voice synthesis into your apps - - - Everything runs on your machine - complete privacy - - +| 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 | ## Use Cases -- **Game Development** — Generate dynamic dialogue for characters -- **Content Creation** — Produce podcasts and video voiceovers -- **Accessibility** — Build text-to-speech tools -- **Voice Assistants** — Create custom voice interfaces -- **Production Pipelines** — Automate voiceover workflows +- **Game development** -- generate dynamic dialogue for characters +- **Content creation** -- produce podcasts and video voiceovers +- **Accessibility** -- build text-to-speech tools for users who need them +- **Voice assistants** -- create custom voice interfaces +- **Production pipelines** -- automate voiceover workflows via the REST API -## Next Steps +## Tech Stack - - - Download and install Voicebox on your machine - - - Get up and running in 5 minutes - - +| Layer | Technology | +|-------|------------| +| Desktop App | Tauri (Rust) | +| Frontend | React, TypeScript, Tailwind CSS | +| State | Zustand, React Query | +| Backend | FastAPI (Python) | +| TTS Engines | Qwen3-TTS, LuxTTS, Chatterbox, Chatterbox Turbo | +| 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 |