Sign in

Repository Index

47,133 repositories indexed

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

4,369–4,392 of 43,641 · Most stars

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.

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

  • intent-recognition
  • stt
  • tts
  • voice