Awesome or creepy? Microsoft VASA-1 is a new artificial intelligence model that turns photos into “talking faces “.
April 22, 2024
Microsoft’s new artificial intelligence research promises a future where you can upload a photo, a voice sample, and create a live, animated talking head of your own face.
VASA-1 takes a single portrait photo and a voice file and turns it into a realistic talking face video, complete with lip sync, realistic facial features and head movements.
The model is currently only a research preview and no one outside the Microsoft Research team is allowed to try it, but the demonstration videos are impressive.
