Artificial intelligence sound studio working in a local environment
Voicebox is an open source artificial intelligence voice studio that allows users to perform voice cloning, dictation and content creation. Developed with the TypeScript language, this platform offers comprehensive tools to manage audio processing processes in the native environment.
Updates
- September 13, 2026: Stars 50,505 → 53,088, latest release v0.5.0 (April 25, 2026).
- August 16, 2026: Stars 48,096 → 50,505, latest release v0.5.0 (April 25, 2026).
- August 2, 2026: Stars 31,156 → 48,096, latest release v0.5.0 (April 25, 2026).
What you get
- Transcribe your own voice or someone else's voice in seconds.
- Provide natural voice-over and dictation in 23 different languages.
- Protect privacy by keeping all audio data on your local computer.
Installation
git clone https://github.com/jamiepine/voicebox.git
cd voicebox
just setup # creates Python venv, installs all deps
just dev # starts backend + desktop appIf you don't write code
I manage the voice transcription and dubbing processes on Voicebox. Help me determine the most appropriate TTS engine for my chosen voice profile, show me how to add emotional emphasis within text, and explain step-by-step how to configure the voicebox.speak car call needed for my local AI agent to respond with voice.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-21: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.