Avatars that listen back.

Until today, every “real-time” AI avatar was the same trick, a generative mouth stitched onto a pre-recorded face, nodding politely while you spoke, the same nod for a joke as for grief. The illusion of listening.

Today, that changes. AVTR-1 generates the whole face, every frame, in real time. New generation of avatars is here, open sourced.