PinnedLoading
- kyutai-labs/moshi
kyutai-labs/moshi PublicMoshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Something went wrong, please refresh the page to try again.
If the problem persists, check theGitHub status page orcontact support.
If the problem persists, check theGitHub status page orcontact support.
Uh oh!
There was an error while loading.Please reload this page.