Atmanity releases real-time avatar model Atmee v2: one photo plus 10 seconds of audio is enough to generate a character capable of video calls
Atmanity releases the real-time avatar model Atmee v2, which can generate a speaking character capable of real-time video calls from just 1 photo and 10 seconds of audio. This model handles rendering of the face and body, while another model, Causeur, drives the character's behavior and responses, making expressions and gestures follow the conversation. Developers can integrate via API and need an invite code from atmee.ai; the company claims it is up to 50 times faster and 10-100 times cheaper than Seedance 2.5 and Wan 3.0.
Why read this
AI score 57
Atmanity releases the real-time avatar model Atmee v2, along with speed and cost comparisons against Seedance 2.5 and Wan 3.0, which can be used to gauge the barrier to deployment for real-time video agents.
Topics
View original postAfter 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.
View original
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.
Body
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
https://t.co/IHutsnXvZ7