About
A 22B parameter model capable of simultaneous audio-visual generation at 47fps on a single GPU. It enables live, conversational interactions with AI characters that match lip movements and expressions to voice in real-time.
Details
- Built with
- Unknown
- Creator
- Source date
- Published on X Jun 20, 2026
- Listed
- Added to Dropday 2h ago
- Evidence
- Strong
The project is demonstrated in a detailed 69-second video by the creator, showcasing real-time synchronized responses, and includes an early access link.
Timeline
Teaser
Video
Playable
Product
Loading…
Media & coverage
sourced from 2 posts
