Jamie Pine · 2026-03-17 · notable
Voicebox — Open-Source Voice Synthesis Studio
Voicebox is a local-first voice cloning studio — a free and open-source alternative to ElevenLabs. Clone voices from seconds of audio, generate speech in 23 languages across 5 TTS engines, all running locally. 17.3k stars.
The open-source ElevenLabs alternative that runs entirely on your machine.
Key specs
| GitHub stars | 17.3k |
|---|---|
| Tts engines | 5 |
| Languages | 23 |
| Audio effects | 8 |
What is it?
Voicebox is a local-first voice synthesis studio offering voice cloning, text-to-speech in 23 languages, audio effects, and multi-track timeline editing. It supports five TTS engines (Qwen3-TTS, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA) and runs completely offline with no data leaving your machine.
How does it work?
Built with Tauri (Rust) for native performance rather than Electron. Supports macOS (MLX/Metal), Windows (CUDA), Linux, AMD ROCm, Intel Arc, and Docker. Voice cloning works from short audio samples. The timeline editor allows multi-voice projects for podcasts and conversations. Post-processing effects include reverb, pitch shift, delay, compression, and filters via Spotify's Pedalboard library.
Why does it matter?
ElevenLabs charges per character and processes audio on their servers. Voicebox gives creators unlimited voice synthesis with complete privacy. The paralinguistic tags like [laugh] and [sigh] enable expressive speech that sounds natural. At 17.3k stars, it's become the go-to open-source voice tool.
Who is it for?
Podcasters, content creators, game developers, accessibility tool builders who want local voice synthesis.
Try it
Download from voicebox.sh or clone from GitHub.