Tavus has introduced Griffin, its first Human Interaction Model (HIM) built for real-time, face-to-face interaction.
Tavus has introduced Griffin, its first Human Interaction Model (HIM) built for real-time, face-to-face interaction.
Griffin processes audio and video continuously, allowing it to keep listening while speaking, react to expressions and pauses, interrupt naturally and generate the full video frame in real time. In Tavus’ live study, 48% of participants believed they were talking to a real person after a one-minute video call, while Griffin-Lite is currently available only as a limited research preview.