Tavus releases real-time video conversation model Griffin; 48% of testers mistook it for a human
Understand the story
On October 2, 2026, The Decoder reported that Tavus launched the Griffin model, which it calls the first Human Interaction Model. The model can process voice, facial expressions, tone, gestures, and pauses in real time and generate video bidirectionally. In Tavus's own research, 48% of participants believed Griffin was a real person after a one-minute video call, compared with a maximum of just 2% for previous systems. Additionally, in independent testing by Nvidia as described by Tavus, Griffin scored 3.83, close to the 3.92 for a real human. The event is still in its launch stage, with no follow-up responses or controversy reported.
AI overview of reporting · Updated 17 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- The DecoderNearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call
Tavus launched Griffin, which it calls the first Human Interaction Model, capable of processing speech, facial expressions, tone, gestures and pauses in real time and generating video bidirectionally. In the company's research, 48% of participants thought Griffin was a real person after a one-minute video call, versus a previous high of 2%; in what Tavus says was independent testing by Nvidia, Griffin scored 3.83, close to 3.92 for a real person.