Kyutai Pocket TTS
Model idkyutai/pocket-tts
PricePrice not published
Checked29 September 2026
Where it stands
72newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- Before it from Kyutai
- Kyutai TTS 1.6B / Kyutai STT + Unmute3 Jul 2025
- Weights
- Weights are public. Licence: CC BY 4.0. See the licence for commercial terms.
How to call it
3 ways to use Kyutai Pocket TTS, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | kyutai/pocket-tts |
huggingface.co | |
| Hugging Face (no cloning variant) | kyutai/pocket-tts-without-voice-cloning |
huggingface.co | |
| GitHub / pip | pocket-tts |
github.com |
Pricing
Price not published.
No price source linked. Checked 29 September 2026.
Specs
- Input
- Text and audio
- Output
- Audio
- Context window
- Not published
- Max output
- Not published
- Open weights
- Yes
- Licence
- CC BY 4.0
- Released
- 13 January 2026
- Status
- Current
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
100M-param TTS with cloning, real time on CPU
~200 ms to first audio and ~6x real time on a MacBook Air M4 CPU; streaming, unbounded text length; voice cloning from audio.
Six languages
Found after launch
English, French, German, Spanish, Portuguese, Italian (multilingual since 2026-05-04).
Notes
Gated on HF (accept prohibited-use terms). Training code released 2026-08-25; 2026-09-28 post describes a ‘drifting’ objective replacing flow matching for the sampler head. pip install pocket-tts. Community WebAssembly ports run in-browser.
Sources: https://huggingface.co/kyutai/pocket-tts , https://github.com/kyutai-labs/pocket-tts , https://kyutai.org/blog/