Chatterbox TTS vs Kyutai TTS
Chatterbox TTS
github.com
Kyutai TTS
kyutai.orgSide by side
| Figure | Chatterbox TTS | Kyutai TTS |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | Yes | — |
| Web | — | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | Yes |
| iOS | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 2 | 2 |
| Spec score · Text-to-Speech Software | 9.0 (#9) | 8.4 (#64) |
| Spec score · Text-to-speech tools | 8.9 (#21) | 8.3 (#75) |
| Export formats | WAV | WAV |
| Founded | 2019 | 2023 |
| Integration | NVIDIA provides a Chatterbox TTS plugin for ACE for Games with CUDA, Vulkan and Windows D3D12 backends. | Kyutai says TTS 1.6B is used in Unmute, its interactive real-time speech demo. |
| Languages | The README lists 23 supported languages for Chatterbox Multilingual. | The Pocket TTS repository lists English, French, German, Portuguese, Italian, Spanish, and Dutch support. |
| License | The code and model listing identify the project as MIT licensed, permitting modification and redistribution subject to the license notice. | The Pocket TTS GitHub repository identifies its license as MIT. |
| Platforms | linux,macos,self_hosted | web,macos,ios,api,self_hosted |
| Product | Chatterbox is a family of open-source text-to-speech models by Resemble AI. | Kyutai describes TTS as two open-source text-to-speech models: Pocket TTS and Kyutai TTS 1.6B. |
| Voice cloning | Models can generate speech conditioned on a short reference audio clip. | Pocket TTS can clone a voice from an audio sample when run locally. |
Plans
Chatterbox TTS
- Chatterbox open-source modelsFree
- Voice AI Research (Chatterbox)Free
In their own words
Chatterbox TTS
Chatterbox TTS is a family of open-source text-to-speech models from Resemble AI. Its listed choices include Turbo, Nano, Multilingual V3, and dedicated single-language models. Turbo supports tags that can prompt reactions such as sighs, gasps, coughs, and laughter; Nano is intended for on-device or CPU use when memory and latency budgets are tight. The README lists 23 languages for Multilingual. The project supports voice cloning, audio input, batch processing, voice isolation, and WAV export. Generated audio carries Resemble AI’s PerTh watermark. The repository is MIT licensed, and its listed plan costs nothing for research and development. Resemble says it has stopped offering voice generation as a commercial product, while its models remain open and free for research and development. The README provides pip and source installation instructions and describes Python 3.11 on Debian 11, with CUDA, CPU, and MPS device options. Listed platforms are Linux, macOS, and self-hosted.