mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 21:00:42 -07:00
Jamie Pine
64dd29d35a
- Created new directory structure for documentation under `/docs2`. - Added `.gitignore` to exclude build artifacts and dependencies. - Introduced `package.json`, `next.config.mjs`, and `postcss.config.mjs` for project configuration. - Implemented MDX components in `mdx-components.tsx` for rendering documentation. - Migrated existing documentation content and created new files for auto-updater and other features. - Established compatibility layer for Mintlify components in `mintlify-compat.tsx`. - Set up OpenAPI documentation in `openapi.json`. - Updated README and migration guide to reflect new structure and usage instructions. - Ensured all components and pages are ready for development and deployment with Fumadocs.
51 lines
2.0 KiB
Plaintext
51 lines
2.0 KiB
Plaintext
---
|
|
title: "Voicebox Documentation"
|
|
description: "Welcome to Voicebox - the open-source voice synthesis studio"
|
|
---
|
|
|
|
## 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.
|
|
|
|
<Frame>
|
|
<img src="/images/app-screenshot-1.webp" alt="Voicebox App Screenshot" />
|
|
</Frame>
|
|
|
|
Unlike cloud services that lock your voice data behind subscriptions, Voicebox gives you:
|
|
|
|
- **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
|
|
|
|
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.
|
|
|
|
## Key Features
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Voice Cloning" icon="microphone">
|
|
Instant cloning from just a few seconds of audio with Qwen3-TTS
|
|
</Card>
|
|
<Card title="Stories Editor" icon="film">
|
|
Multi-track timeline for creating conversations and narratives
|
|
</Card>
|
|
<Card title="Full API" icon="code">
|
|
REST API for integrating voice synthesis into your apps
|
|
</Card>
|
|
<Card title="Local-First" icon="shield">
|
|
Everything runs on your machine - complete privacy
|
|
</Card>
|
|
</CardGroup>
|
|
|
|
## Get Started
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Installation" icon="download" href="/docs/overview/installation">
|
|
Download and install Voicebox on your machine
|
|
</Card>
|
|
<Card title="Quick Start" icon="rocket" href="/docs/overview/quick-start">
|
|
Get up and running in 5 minutes
|
|
</Card>
|
|
</CardGroup>
|