whatmodel.sh / tts / Chatterbox Turbo
Chatterbox Turbo
↗ share
+ contribute
Chatterbox Turbo is an open-weights text-to-speech model from Resemble AI, released December 2025. Its published size is 0.35B parameters. Licence: mit.
Catalogue identity notes
ResembleAI/chatterbox-turbo (350M English model with a one-step distilled decoder), loaded by ChatterboxTurboTTS in the official chatterbox-tts package. Distinct from Chatterbox and Chatterbox Multilingual.
$ how it compares
Scored text-to-speech models released closest to Chatterbox Turbo, out of 148 with a score, then more from Resemble AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 25 |  Qwen3-TTS 12Hz 1.7B Base | 65±1 | local | ||
| 28 |  Fun-CosyVoice3-0.5B-2512 | 64±1 | local | ||
| 34 |  GLM-TTS | 63±2 | local | ||
| 41 |  Inworld TTS-1.5 Max | 62±3 | api $10.00/M chars | ||
| 78 |  Gradium TTS | 51±3 | api $38.00/M chars | ||
| more from Resemble AI | |||||
| 69 | Chatterbox Multilingual V3 | 54±10 | local | ||
| 86 | Chatterbox | 50±5 | api $25.00/M chars +local | ||
see all text-to-speech models · find the ones that fit your machine
$ where to run it
Other ways to run it
- Run it as published · needs ~2.99 GB · from github.com/resemble-ai (official)
pip install chatterbox-tts && python -c "import torchaudio as ta; from chatterbox.tts_turbo import ChatterboxTurboTTS; m = ChatterboxTurboTTS.from_pretrained(device='cpu'); ta.save('test-turbo.wav', m.generate('Hi there, Sarah here from MochaFone calling you back [chuckle], have you got one minute to chat about the billing issue?'), m.sr)"
Official weights and documentation: huggingface.co/ResembleAI ↗
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json