Text to speechSpeech to text

Kyutai STT, TTS и Pocket TTS

Streaming speech recognition and synthesis models from the makers of Moshi: they start speaking and transcribing without waiting for the end of a phrase. Pocket TTS (100M) runs on a CPU. English, French and a few other European languages, no Russian.

Developer
Kyutai, France
First release
Jun 2025
Latest release
Apr 2026
Sizes
100M (Pocket TTS) – 2.6B
License
Commercial use allowedCC BY 4.0 (weights), code MIT and Apache 2.0
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Media and production, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Streaming speech transcription for voice bots
  • Voicing replies with minimal delay
  • Speech synthesis on a server without a GPU (Pocket TTS)

Where it is used

Voice botsCall centersProduct development

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Pocket TTS 2.0 (6 европейских языков)
  2. Pocket TTS (100M)
  3. Kyutai TTS 0.75B
  4. Kyutai TTS 1.6B
  5. Kyutai STT 1B (английский и французский)
  6. Kyutai STT 2.6B (английский)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Kyutai STT, TTS и Pocket TTS be used in a commercial project?

Yes. License: CC BY 4.0 (weights), code MIT and Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Kyutai STT, TTS и Pocket TTS need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Kyutai STT, TTS и Pocket TTS support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Kyutai STT, TTS и Pocket TTS and what does it cost?

The Kyutai STT, TTS и Pocket TTS weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Voice assistantsMoshi / HibikiKyutai · FranceCommercial use with conditions

A voice assistant that listens and speaks at the same time, with no delay for recognition and synthesis. Hibiki does simultaneous speech-to-speech translation between several European languages.

DetailsText to speechKokorohexgrad (independent developer) · not disclosedCommercial use allowed

A tiny speech synthesis model (82M) that sounds on par with large ones. Runs on a regular CPU; English and a few other languages, no Russian.

DetailsSpeech to textNVIDIA Parakeet / Canary / Nemotron SpeechNVIDIA · USACommercial use with conditions

Fast NVIDIA speech recognition models, including streaming ones for real-time use. Parakeet TDT v3 and Nemotron 3.5 ASR understand Russian.

Details

Source: github.com/kyutai-labs/pocket-tts/releases. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.