Griffin
Tavus unveiled Griffin, a Human Interaction Model for real-time video conversation. In the company's test, 48% of participants thought Griffin-Lite was a real person.
Griffin is described as a model that understands and generates face-to-face conversation, reacting to facial expressions and pauses as well as words. Tavus reports audio-video latency of 0.43 seconds on NVIDIA H100 chips. Access to Griffin-Lite is limited to select trusted testers while Tavus works on disclosure features and safety.
- Date
- Thursday 1 October 2026
- Lab
- Tavus
- Kind
- model
- Access
- research preview
Figures
| Measure | Value | Measured by |
|---|---|---|
| Participants who believed Griffin-Lite was human after a one-minute video call | 26 of 54 (48%) Tavus's previous system scored 1 of 41 | company |
| Audio-video latency | 0.43 seconds on NVIDIA H100 chips | company |
Results come from Tavus's own study and have not been independently verified.
Sources
This record was checked against its sources on 8 October 2026. How we check