Nearly half of test subjects mistook Tavus' AI video avatar for a real person on a one-minute call
Tavus launched Griffin, a real-time conversational video model that 48% of test subjects mistook for a real human on one-minute calls.
Tavus introduced Griffin, billed as the first "Human Interaction Model" (HIM), processing speech, facial expressions, tone, gestures, and pauses while generating real-time video conversation. In Tavus testing, 48% of participants believed Griffin was a real person after a one-minute call, versus a 2% maximum for previous systems. An Nvidia test of perceived humanness scored Griffin 3.83 versus 3.92 for actual humans and 2.80 for the previous best AI. Griffin-Lite is available as a research preview, with a fuller release gated on addressing safety concerns; the San Francisco startup has raised about $64 million.
- Griffin processes speech, facial expressions, gestures, and pauses in real-time two-way video
- 48% of one-minute-call participants believed Griffin was human; prior systems peaked at 2%
- Nvidia humanness test scored Griffin 3.83 versus 3.92 for humans, 2.80 for previous best AI
- Griffin-Lite research preview available; full release pending safety concerns
Full article232 words · extracted from the-decoder.com · click to collapse
Tavus has introduced Griffin, what the company calls the first "Human Interaction Model" (HIM), a class of model designed to understand and carry on face-to-face conversations in real time. Griffin processes speech, facial expressions, tone of voice, gestures, and pauses while both receiving and generating video.
In a Tavus study, 48 percent of participants believed Griffin was a real person after a one-minute video call. Previous systems maxed out at two percent. In what Tavus describes as an independent Nvidia test measuring how human an AI feels in direct audio-video conversation, Griffin scored 3.83 points. Actual humans scored 3.92, the previous best AI model hit 2.80.
A preview called Griffin-Lite is available to "select testers as a research preview," with a more capable version coming once "safety concerns are addressed." Tavus lists tutoring, practicing difficult conversations, and camera-based tech support as potential use cases.
The San Francisco AI startup was founded in 2020 and has raised about $64 million. It started out building personalized AI videos for sales and marketing, then expanded into live video conversations with digital personas. More details on Griffin are in the Tavus research report.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Text extracted automatically; images, tables and formatting may be missing. Original: https://the-decoder.com/nearly-half-of-test-subjects-mistook-tavus-ai-video-avatar-for-a-real-person-on-a-one-minute-call/