Griffin is Tavus's Human Interaction Model for face-to-face, real-time conversation. Unlike typical voice bots, it sees, hears, and talks at the same time. It picks up on pauses, facial expressions, gestures, and what's happening on camera, so conversations feel natural and responsive. In a live one-minute video call, 48% of participants believed they were talking to a real person. Griffin-Lite is now available as a research preview to a small group of early testers, offering full-duplex video-to-video interaction and 720p generation. It's a big step toward more human AI conversations.
Categories:
Artificial Intelligence
Launch Team / Built with
HR
QF
Launch Date:
October 14, 2026