Tavus CEO Hassaan Raza on Griffin: 'I had no idea I was watching our model'

Raza says Tavus's goal is for talking to a machine to feel like talking to a friend or coworker, and that Griffin captures conversational nuances (expressions, posture, turn-taking); the first time he saw it used he could not tell it from a normal video call.

The whole point of building Tavus has been simple: talking to a machine should feel as natural as talking to a friend or coworker.

It’s hard to describe all the tiny nuances that make a conversation feel human. The little expressions. Moving around in your chair. Knowing when to speak and when to listen. The dance of it all.

Griffin is by far the closest anyone has come to a model that can capture those nuances. The first time I saw it being used, I had no idea I was watching our model rather than just a normal video call.

I’m so incredibly proud of this team and what they’ve built.

Quoting @tavus: Introducing Griffin, the first model to pass the video Turing test.

48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video.

It’s the first Human Interaction Model (HIM).

Media: https://video.twimg.com/amplify_video/2105707530441961472/vid/avc1/1280x720/z2PhCVA7ZuzWtiGg.mp4?tag=29

views 3370821 · likes 4108 · reposts 309 · replies 802 (at fetch time)

Archived 2026-10-02 via fxtwitter (unofficial).