kyutai-labs

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.

A TTS that fits in your CPU (and pocket)

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

Make text LLMs listen and speak

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---...

A real-time and multilingual speech translation model

Kyutai with an "eye"

MoshiRAG is a compact full-duplex speech language model augmented with asynchronous knowledge retrieval to improve factuality without sacrificing real-time interactivity.

To bring back voice to those who lost it

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

Official implementation and models for OVIE (One View Is Enough! Monocular Training for In-the-Wild Novel View Generation)