Please use portrait mode

Rotate your device to continue.

RepoVerseBack to archive
Rare

moshi

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.

ATK
7904
DEF
5606

kyutai-labs/moshi

Rare · Base · Genesis

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.

Attack7,904
Defense5,606

Drag the card to turn it. Use the flip button to see the back.

View on GitHub
Open card page