Tavus Griffin Passes Video Turing Test

// 57m agoMODEL RELEASE

Tavus Griffin Passes Video Turing Test

Tavus introduced Griffin, a full-duplex Human Interaction Model that simultaneously sees, hears, speaks, and responds with humanlike timing and expression. Its Griffin-Lite research preview convinced 48% of participants they were speaking with a real person. Tavus

// ANALYSIS

Griffin is a major interface breakthrough, but its ability to blur the human-AI boundary makes careful disclosure essential.

–Unified video-to-video generation handles speech, gaze, facial expression, gesture, and turn-taking continuously.
–Griffin-Lite scored ahead of published commercial and open-source baselines on NVIDIA’s VideoFDB benchmark.
–The system enables more natural tutors, coaches, support agents, and collaborative assistants.
–Griffin-Lite remains limited to select testers while Tavus develops stronger safety and disclosure measures.

// TAGS

griffinmultimodalvisionspeechvoice-agentagentevaluationsafety

DISCOVERED

57m ago

2026-10-01

PUBLISHED

1h ago

2026-10-01

RELEVANCE

9/ 10

AUTHOR

hudsonsauder11

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL1h ago

Tavus Griffin Passes Video Turing Test

Tavus introduced Griffin, a real-time, full-duplex video-to-video model that sees, hears, interrupts, gestures, and responds during face-to-face conversations. In Tavus’s one-minute study, 26 of 54 participants believed Griffin-Lite was a real person; the research preview is limited to selected testers.

UPDATE1h ago

Tesana Rebuilds Game Stack Around Three.js

Tesana has rebuilt its AI game-generation platform around Three.js, replacing its Godot-based pipeline with web-native TypeScript games. The company says average generation time has fallen from roughly 60 minutes to under five.

MODEL1h ago

Chutes releases Parallax 8B Theta model

Chutes released the Parallax 8B Theta model after training it across distributed consumer GPUs. Founder Jon Durbin presented the project at Exploit Summit as a blueprint for cheaper, more resilient AI infrastructure.