AI video company Tavus has introduced Griffin, a system it describes as the first Human Interaction Model built for real-time face-to-face conversation. The company said Griffin can speak, watch, listen, and react in real time to a counterpart’s facial expressions, movements, pauses, and interruptions during a live exchange.
In a company-run test, Tavus recruited 54 participants from the United States and Europe and had them join a one-minute video call with Griffin-Lite without telling them in advance that the other side was AI. According to Tavus, 26 participants, or 48%, believed they had been speaking with a real person. By comparison, Tavus said its previous-generation Phoenix-4.5 recorded 1 mistaken judgment out of 41 participants, or 2.4%, in a similar test.
Tavus used those results to argue that Griffin is the first model to pass a real-time video Turing test. The company also said Griffin-Lite ranked first on NVIDIA’s VideoFDB full-duplex audio-video benchmark with a score of 3.83 out of 5, close to the human reference score of 3.92. The previously highest public baseline, Gemini 2.5 + Anam, scored 2.80. Tavus noted that the test was self-organized, involved only 54 people, and has not yet been independently replicated at larger scale. Griffin-Lite is currently available only to a small group of testers.
AI video company Tavus has launched Griffin, a model designed for real-time face-to-face conversation. Tavus describes it as the first Human Interaction Model.
According to the company, Griffin can speak while watching and listening, then respond in real time to a counterpart’s facial expressions, movements, and pauses. If a user interrupts mid-conversation, the system can stop immediately.
26 of 54 participants thought they were talking to a real person
Tavus said it recruited 54 participants from the United States and Europe and asked them to join a one-minute video call with Griffin-Lite without telling them beforehand that the other side was AI. The company said 26 participants, or 48%, believed they had just spoken with a human.
For comparison, Tavus said its previous-generation Phoenix-4.5 produced 1 mistaken judgment out of 41 participants, or 2.4%, in a similar test. Based on that result, Tavus said Griffin is the first model to pass a "real-time video Turing test."
The test was organized by Tavus and has not been independently replicated at larger scale
Tavus also noted that the test was organized internally, involved only 54 participants, and has not yet seen larger independent replication.
Score of 3.83/5 on VideoFDB
The company also said Griffin-Lite ranked first on NVIDIA’s VideoFDB full-duplex audio-video benchmark. Tavus reported a score of 3.83 out of 5, close to the human reference score of 3.92. The previously highest public baseline, Gemini 2.5 + Anam, scored 2.80.
Griffin-Lite is currently available only to a small number of testers and has not yet been formally released to general customers.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
