Watch the Mona Lisa Rap, via Microsoft’s AI: It’s as Freaky as You Think

Many mysteries persist about the human condition: why are we here? Who created the universe? And above all, could the Mona Lisa rap?

Microsoft announced a new artificial intelligence technology called VASA-1, which can turn a photo of a person’s face and a short clip of their voice into a realistic, computer-powered video. And with this breakthrough, the company was able to create a realistic video of Leonardo da Vinci’s famous painting, the Mona Lisa, performing actress Anne Hathaway’s 2011 viral rap, Paparazzi.

Microsoft’s video is the latest example of the rapid progress tech companies are making with AI tools, although a rapping Mona Lisa arguably straddles the line between quirky and scary.

The software giant’s new technology is far from the only use of AI to interpret and experience art, or the broader world of media. Microsoft partner startup OpenAI, for example, has created equally eye-catching videos using its text-to-video conversion model, Sora, which can create ultra-realistic videos from text prompts. Google has a similar tool called Lumiere.

These tools are in limited availability. When it comes to AI tools you can use every day, be sure to check out CNET’s hands-on reviews of image generators from Adobe Firefly, OpenAI’s Dall-E 3, and Google’s ImageFX, as well as reviews of chatbots including ChatGPT, Gemini and Claude.

From deepfake to reality

Microsoft’s technology may seem like nothing new. Researchers have been showing incredibly realistic video manipulations for years, often calling them deepfakes. Among the most impressive deepfakes is one from the Massachusetts Institute of Technology, which used AI technology in 2019 to make it appear as if President Richard Nixon was giving a speech he never actually gave.

Experts have expressed growing concern that deepfakes could be used to spread misinformation.

These concerns haven’t stopped app developers from effectively providing a basic version of what Microsoft has developed. Such apps have become so popular that cybersecurity researchers warn that photographs people upload can be used to advance technology without the consent of the owner or subject.

Microsoft hopes these technologies can do more good than harm.

“While recognizing the possibility of misuse, it is imperative to recognize the substantial positive potential of our technique,” ​​the company wrote in a blog post announcing VASA-1. “Benefits – such as improving educational equity, improving accessibility for people with communication difficulties, providing coaching or therapeutic support to those who need it, among others – highlight the importance of our research and other related explorations.”

Microsoft added that it is “dedicated to developing AI responsibly, with the goal of advancing human well-being.”

Editor’s note: CNET used an AI engine to create several dozen stories, labeled accordingly. The note you are reading is attached to articles that cover the topic of AI in depth, but are created entirely by our expert editors and editors. To find out more, see our AI Policy.