Post-Cutoff

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

Hassaan Raza @hassaanrazaX

Why it matters

First-hand launch post by Tavus’s CEO with ~3.35M views, more reach than most lab announcements that week.

Summary

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.

Archived text

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).

Source: x.com/hassaanraza/status/2105709935074185546Archived 2026-10-02 via fxtwitter (unofficial).Counts: 3,370,821 views, 4,108 likes, 309 reposts, 802 replies (at fetch time)Media: video poster

Cited in

  1. Media generation 93 days after the cutoff

    Tavus unveils Griffin, a real-time face-to-face video model it says is the first to pass a ‘video Turing test’ (48% thought it was human)