Tavus previews Griffin, a Human Interaction Model that sees, hears and speaks like a person

_jaydeepkarale · x · 2026-10-03

Tavus, a research lab focused on natural human-machine communication, previewed Griffin, a "Human Interaction Model" that can see, hear, speak and make eye contact — aiming to understand expression, tone and context beyond words. The model is not publicly available yet; the announcement was a limited research preview ahead of a safe public release.

Related event: Tavus launches Griffin, real-time video conversation model that fools 48% of testers(17 posts)→

Original post →

More from Models

Models channel →