#1414th of 51 in VoiceFor voice, speech and music
chatterbox
Open text-to-speech models with zero-shot voice cloning in 23+ languages
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 27.1k
- License
- MIT
- Last commit
- Jul 2026
- Last release
- Jun 2025
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Chatterbox is a family of Python text-to-speech models from Resemble AI that clone a voice from a short reference clip. It includes a 500M multilingual V3 model covering 23 languages, a 350M English Turbo model for low-latency agents, and a 110M Nano model for CPU inference. Turbo and Nano support paralinguistic tags such as [laugh] and [cough].
Who it is for: Developers adding voice cloning and TTS to agents or apps
Strengths
- Model sizes from 110M (Nano) to 500M (Multilingual V3) cover CPU through GPU use
- Zero-shot voice cloning from a reference clip, including across languages
- Turbo decoder distilled from 10 steps to one for lower latency
- Every output carries a Perth watermark, with a documented extraction script
Weaknesses
- Turbo and Nano are English only; multilingual needs the 500M model
- Tested only on Python 3.11 on Debian 11; dependencies pinned
- No built-in server, web UI or Docker setup; Python API only
- Last tagged release is 2025-06-13, while newer models ship from main
What it needs
- GPU optional
- Needs PyTorch, torchaudio, Hugging Face model weights
- Models: Chatterbox-Turbo 350M, Chatterbox-Nano 110M, Chatterbox-Multilingual V3 500M, Single Language Pack (6 finetunes), Chatterbox 500M English
Also in Voice
See all 51| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 83 out of 100 |
| 2 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 80 out of 100 |
| 3 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 78 out of 100 |
| #4 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 71 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 71 out of 100 |