kyutai-labs
★ 11,153moshi
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.
HYSEN LABS DIRECTORY
Verified repositories, classifications and analysis from the kyutai-labs organization.
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.
Make text LLMs listen and speak