kyutai-labs/hibiki

A real-time and multilingual speech translation model

Confucius4-R2T2: A Low Latency and High Accuracy Real-Time Speech Recognition Model

Simultaneous translation model for 200 languages

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

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.

Foundational Models for State-of-the-Art Speech and Text Translation

NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models