AURA x Unmute

AURA is a 1.3B speech-to-video generative model that runs in real time on a single GPU (the current demo runs at 480px). Here we use it to give a face to Unmute, our cascaded voice AI. Read more

The demo is starting up

We just updated it, or it is restarting. This usually takes a few minutes (up to about 10 for the face model). Nothing is broken: this page checks every few seconds and opens the demo by itself when everything is ready.

Starting the face model…

Website:starting…

Speech recognition:starting…

Language model:starting…

Voice:starting…

Face model:starting…

Waiting for 0:00.