OpenSource-Hub
V

voicebox

SHA-256
31.1k stars·AI Productivity·SHA-256 checksum verified

The open-source AI voice studio. Clone, dictate, create. A local-first alternative to ElevenLabs and WisprFlow, offering complete privacy and full voice I/O on your machine.

Smart Download

Download Download Version

v0.5.0 · 560.1 MB

Open-source AI voice studio: clone voices, generate speech, and dictate — all locally, with full privacy.

Core Features

  • 7 TTS engines with 23 languages support
  • Zero-shot voice cloning from seconds of audio
  • Global dictation hotkey for any text field
  • Agent voice output via MCP protocol
  • Post-processing effects: pitch, reverb, delay, etc.

What It Can't Do

  • First launch downloads models (~2-8 GB); stable internet required. 2. No pre-built Linux binaries yet; build from source (see docs). 3. Some TTS engines (e.g., Chatterbox Turbo) need ~4GB+ GPU VRAM; CPU works but is slower. 4. Global dictation hotkey may need extra configuration on some Linux DEs.

Use Cases

  • Content creators: generate multilingual voiceovers for videos and podcasts
  • Developers: add voice capabilities to personal AI assistants or chatbots
  • Accessibility: hands-free dictation for faster text input

Detailed Introduction

Voicebox is a local-first AI voice studio that serves as a free, open-source alternative to ElevenLabs and WisprFlow combined. It enables voice cloning from seconds of audio, speech generation in 23 languages across 7 TTS engines, global dictation via hotkey, and voice output for MCP-aware AI agents. All processing runs locally, ensuring complete privacy. Unlike cloud incumbents, Voicebox bridges input and output with a bundled local LLM for refinement and per-profile personas, making it a comprehensive voice I/O solution that works offline.

Tags

voice cloningtext-to-speechopen sourcelocal-firstspeech recognitionAI voice studioprivacy

Getting Started

1

Download installer

Click the button above to download the installer for your system

2

Install the software

Open the downloaded dmg file, then drag the app to Applications

3

Download the appropriate installer for your OS (DMG for macOS, MSI for Windows)

4

Double-click the installer and follow the setup wizard (macOS: drag to Applications folder)

5

Launch the app; it will automatically download required models. Wait a moment and start using.

Install Guide
  1. Download the appropriate installer for your OS (DMG for macOS, MSI for Windows)
  2. Double-click the installer and follow the setup wizard (macOS: drag to Applications folder)
  3. Launch the app; it will automatically download required models. Wait a moment and start using.
File Integrity

SHA-256 checksum verified

Checksum extracted from GitHub official Release page

SHA256 Checksum

44d883cde3c3179907f31af54908727a0d7e3a4f99f6bad8be791fbc810d6fc3

This checksum is extracted from the GitHub Release page. Verify file integrity after download.

All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.

Open Source Transparency

View GitHub Source
Environment Guide

Uninstall Info

macOS: Drag Voicebox from the Applications folder to Trash. Windows: Uninstall via 'Settings > Apps > Apps & features'.

No Extra Dependencies

Ready to use after download. No additional runtime required.

Project Info
LicenseMIT
Last Updated2026-06-21T06:53:02Z
GitHub RepositoryOfficial Website

Similar Projects