Atmee v2 发布 实时视频化身赋能 AI 智能体

Rohan Paul (@rohanpaul_ai) · 2026-11-04 18

Live video is the next interface for AI agents, and the tech is ready for it now.

Atmanity released Atmee v2, an AI a real-time avatar model, that turns 1 photo and 10 seconds of someone’s voice into a talking character you can video-call live.

i.e. any app can now add a face to its AI, the way it can already add a chat box or a voice.

Two models do the work. Atmee v2 renders the face and body. A second model, Causeur, drives how the character behaves and responds, so its expressions and gestures follow the conversation.

Text and voice agents work well. A face makes tutors, coaches and support agents a lot easier to talk to.

Developers get it through an API, with an invitation code from atmee[.]ai

↳ 引用 @yuchenping (Chen-Ping Yu): After Google acquired my AR startup, I started thinking about the next interface, this time for AI. Text and voice work fine, just like DOS did before the Mac. But nothing’s more intuitive than face to face.

After two years of research, today we’re launching Atmee v2: a real-time avatar model that makes live video agents feel truly life-like.

• Any character from 1 image + 10s of audio • Contextual expressions, gestures, even interacting with the environment • Live video calls, voice only, or video generation

At its core, Atmee v2 is a video foundation model, it can render anything, but it’s built to excel at characters, which is what video models like Seedance 2.5 and Wan 3.0 are mostly used for. In comparison: Atmee v2

• Up to 50x faster • 10-100x cheaper

Build tutors, sales coaches, support agents, companions, game characters, even whole living worlds. The interface after text and voice starts today.