Artificial Intelligence is getting smarter, funnier, and in some ways creepier. Arguably a photo of the most famous painting, the Mona Lisa is capable of doing more than just smirking, with the help of Microsoft’s brand new artificial intelligence technology.

Visit for more information

Researchers at Microsoft detailed VASA-1, a new AI model they developed that takes still images of a face with an audio clip of anyone speaking, and it automatically creates a pretty realistic video of that person’s photo speaking. The videos are compelling, with lip-syncing, and natural face, and head movements—spooky stuff. 

Get this: in one demo video, the Microsoft researchers animated an image of the Mona Lisa to spit a comedic rap, originally by actor Anne Hathaway. Well at least it wasn’t a real artist, then we’d have more AI controversy on our hands. 


The output result may be entertaining but may also feel jarring in the product’s authenticity. It just feels too real for some. Now Microsoft said the tech could work within educational applications or, as they put it, “improving accessibility for individuals with communication challenges,” or even virtual companions for humans. Now, that all sounds good, but it may be used for impersonating people and other nefarious uses. Imagine this AI technology used to disrupt creative industries from film to advertising and more.

Microsoft says it is not releasing the VASA-1 model to the public just yet. “We are opposed to any behavior that creates misleading or harmful contents about real persons,” Microsoft researchers said in a recent blog post. They added that they have “no plans to release” the product publicly “until we are certain that the technology will be used responsibly and in accordance with proper regulations.”

The Mona Lisa rapping and all that is fun and games, but until this technology can be responsibly managed, it seems like it’s ripe for potential issues in a world where there’s already enough misinformation floating around. So, the jury is out on this one.