Map / Core AI / Foundation Models / Moshi

Moshi

Kyutai's open full-duplex speech model for real-time voice dialogue

CuratedSpeech & Audio Models

I use this adds Moshi to your stack and finds people with similar stacks. Every mark feeds the counts on Pulse. Sign in to mark it.

No ratings yet

Who uses it

0 use this

0use it now

0tried it, dropped it

0want to try

Nobody has marked it yet. Press I use this, Tried it or Want to try to be the first.

Ratings

Only from people who use it or tried it

No ratings yet

The first rating comes from someone who uses Moshi or tried it.

Use Moshi?

What it does

Moshi is a speech-text foundation model from the Paris lab Kyutai that listens and talks at the same time for natural spoken dialogue. It uses Kyutai's Mimi streaming audio codec. Code is on GitHub under MIT and Apache licences, weights (Moshiko and Moshika voices) are CC-BY 4.0, and it runs on PyTorch, MLX for Mac and iPhone, and Rust.

Alternatives on the map

All 107 alternatives

Foundation Models, starting with the other Speech & Audio Models.

Compare with

People who use it also use

Not enough marks yet to tell. When people who use Moshi mark the rest of their stack, it shows up here.

Open website