Griffin by Tavus

Product Hunt Models
human-interaction-model real-time-video full-duplex avatar conversational-ai video-generation

Summary

Tavus 推出 Griffin——号称全球首个「人类交互模型」，可实时看、听、说并响应停顿、表情和手势，一次一分钟视频通话中 48% 的参与者误以为在和真人对话。Griffin-Lite 作为研究预览向早期测试者开放，支持全双工视频到视频交互及 720p 生成。

<p> World's First Human Interaction Model </p> <p> <a href="https://www.producthunt.com/products/griffin-by-tavus?utm_campaign=producthunt-atom-posts-feed&amp;utm_medium=rss-feed&amp;utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1266940?app_id=339">Link</a> </p>
Original Article
View Cached Full Text

Cached at: 10/08/26, 01:59 PM

# Griffin by Tavus: World's First Human Interaction Model | Product Hunt Source: [https://www.producthunt.com/products/griffin-by-tavus](https://www.producthunt.com/products/griffin-by-tavus) Griffin is Tavus’s Human Interaction Model for face\-to\-face, real\-time conversation\. It sees, hears, and talks at the same time, responding to pauses, expressions, gestures, and what’s happening on camera\. In a live one\-minute video call, 48% of participants believed they were talking to a real person\. Griffin\-Lite is available as a research preview to select early testers, with full\-duplex video\-to\-video interaction and 720p generation\.

Similar Articles

Natural Conversations with GPT-Live

YouTube AI Channels

OpenAI showcases breakthrough in personalization and naturalness of the new voice model, capable of natural brainstorming conversations, displaying empathy and timely interjection, approaching human conversation rhythm.

@elonmusk: Try Grok Voice

X AI KOLs Following

Grok Voice 3.0 发布，被称为全球最智能的语音到语音模型，响应时间低于1秒，面向客服通话场景且成本低于其他前沿模型。

@miramurati: Today we're sharing our work on interaction models. A new class of model trained from scratch to handle real-time inter…

X AI KOLs Following

Mira Murati's team showcased a preview of the new interaction model. Trained from scratch, it natively supports full-duplex real-time audio and video conversations, instant interruptions, multi-language translation, and dynamic multi-tasking. The demonstration verified its core capabilities in low-latency streaming interaction, multimodal perception, and concurrent task execution.