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.

We built this live talk show demo to show that live avatars aren’t just for video calls. They can be embedded seamlessly into any application.

From 1:22, the host and the guest are two Atmee v2 avatars talking to each other, live and unscripted.

Video generation is a side job for Atmee v2, but it’s surprisingly good at it. General models still have the edge on landscapes and physics. But most AI videos are about characters, and it’s hard to beat our speed and cost.

Same image, same prompt. Seedance 2.5 vs. Atmee v2:

Seedance 2.5: 233.6 s, $0.50
Atmee v2: 3.5 s, about a cent

Across every major video model at 480p and 720p, Atmee v2 is the cheapest by a wide margin, and real time or close to it. Charts below.

Two more mobile demos of Atmee v2 dropped into an app: a personal DJ inside your music player, and artwork you can actually talk to.

Learning can be fun: a cartoon animal tutor embedded in a math app, and a personal assistant in the shape of your favorite robot.

We tried something different: turning our avatars into 3D characters and dropping them into games, and you can actually talk to the people in them. And a fitness app where your favorite character pumps you up.

Even a world? This started as a quick experiment: a small alley in Taipei as the starting image, and the same Atmee v2 model generating the scene continuously, live and controllable. There are still distortions and artifacts, but for a live avatar model it hints at where we’re going: an Agentic World Model, a world with life-like agents that behave like people. After all, what’s a world without the people in it?

Want to get access? Drop a line here: atmee.ai/v2signup