Microsoft has developed an AI technology called VASA-1 that can create a realistic video of someone's face and voice.
Using VASA-1, the software giant was able to create a video of Leonardo da Vinci's famed painting, the "Mona Lisa", rapping to US actress Anne Hathaway's viral 2011 rap, "Paparazzi".
According to CNET, Microsoft's AI video showcases rapid advancements, while a rapping Mona Lisa straddles the line between quirky and creepy.
Additionally, OpenAI and Google have also developed text-to-video models, Sora and Lumiere, respectively, to create visually appealing videos from text prompts, but they are in limited availability.
CNET reported that researchers have experimented with lifelike video manipulations, known as deepfakes, for years, which has increasingly worried experts over the spread of disinformation.
However, app developers continue to effectively provide a basic version of what Microsoft has developed.
Because of their popularity, cybersecurity researchers warn that photographs people upload may be used to help advance the technology without the owner or subject's consent.
However, Microsoft hopes for the technology to do more good than harm.
"While acknowledging the possibility of misuse, it's imperative to recognize the substantial positive potential of our technique," the company wrote in a blog post announcing VASA-1.
"The benefits – such as enhancing educational equity, improving accessibility for individuals with communication challenges, offering companionship or therapeutic support to those in need, among many others – underscore the importance of our research and other related explorations."
The company added that it is "dedicated to developing AI responsibly, with the goal of advancing human well-being."