Skip to content
@kyutai-labs

kyutai

Kyutai - Open Science AI Lab

Popular repositories Loading

  1. moshi moshi Public

    Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

    Python 9.6k 878

  2. pocket-tts pocket-tts Public

    A TTS that fits in your CPU (and pocket)

    Python 3.1k 352

  3. delayed-streams-modeling delayed-streams-modeling Public

    Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

    Python 2.8k 296

  4. hibiki hibiki Public

    Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…

    Rust 1.4k 110

  5. unmute unmute Public

    Make text LLMs listen and speak

    Python 1.2k 201

  6. moshi-finetune moshi-finetune Public

    Python 375 56

Repositories

Showing 10 of 25 repositories
  • moshi Public

    Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

    kyutai-labs/moshi’s past year of commit activity
    Python 9,599 Apache-2.0 878 64 13 Updated Feb 11, 2026
  • invincible-voice Public

    To bring back voice to those who lost it

    kyutai-labs/invincible-voice’s past year of commit activity
    TypeScript 33 MIT 5 3 (3 issues need help) 1 Updated Feb 11, 2026
  • pocket-tts Public

    A TTS that fits in your CPU (and pocket)

    kyutai-labs/pocket-tts’s past year of commit activity
    Python 3,147 MIT 352 29 (9 issues need help) 11 Updated Feb 10, 2026
  • flashy Public

    Framework for writing deep learning training loops. Lightweight, and retaining full freedom to design as you see fits. It handles checkpointing, logging, distributed, compatibility with Dora, and more!

    kyutai-labs/flashy’s past year of commit activity
    Python 4 MIT 0 0 0 Updated Feb 4, 2026
  • delayed-streams-modeling Public

    Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

    kyutai-labs/delayed-streams-modeling’s past year of commit activity
    Python 2,842 Apache-2.0 296 37 0 Updated Jan 26, 2026
  • unmute Public

    Make text LLMs listen and speak

    kyutai-labs/unmute’s past year of commit activity
    Python 1,173 MIT 201 28 (3 issues need help) 0 Updated Jan 23, 2026
  • dora Public

    Dora is an experiment management framework. It expresses grid searches as pure python files as part of your repo. It identifies experiments with a unique hash signature. Scale up to hundreds of experiments without losing your sanity.

    kyutai-labs/dora’s past year of commit activity
    Python 5 MIT 0 0 0 Updated Jan 22, 2026
  • tts_longeval Public
    kyutai-labs/tts_longeval’s past year of commit activity
    Python 30 MIT 2 0 0 Updated Jan 22, 2026
  • sphn Public

    python bindings for symphonia/opus - read various audio formats from python and write opus files

    kyutai-labs/sphn’s past year of commit activity
    Rust 77 Apache-2.0 7 1 0 Updated Jan 7, 2026
  • ARC-Encoder Public
    kyutai-labs/ARC-Encoder’s past year of commit activity
    Python 26 Apache-2.0 3 0 0 Updated Jan 5, 2026

Most used topics

Loading…