Microsoft researchers recently debuted a new AI model, VASA-1, that can use a still image of a face and an audio clip of a person speaking to create a video of the person in the photo speaking.
The researchers shared their model in a demo video of the Mona Lisa reciting a comedic rap from actor Anne Hathaway. The videos can be made with images of photorealistic faces, cartoons or artwork.
Microsoft said the technology could be applied in educational settings, used to create virtual human companions or to improve accessibility for those with communication challenges. However, there’s concern that it could also be used to impersonate real people.
Microsoft says it doesn’t plan to make the VASA-1 model available to the public right now. “We are opposed to any behavior to create misleading or harmful contents of real persons,” Microsoft researchers said in a blog post.
