Meta Reveals Tool for converting images into sound-enhanced videos

Meta has introduced a groundbreaking generative artificial intelligence model that allows users to create short videos with sound from text prompts and photos. The announcement came on Friday and showcased what the tech giant calls “Meta Movie Gen.”

Meta hailed this development as a significant advance in the field of AI aimed at making video and audio generation easier. The company plans to gather feedback from filmmakers and YouTubers as it works to bring this innovative video-generating AI to the public, although no specific release date has been given yet.

In a post, Meta emphasized that although generative AI offers many exciting possibilities, it should not be seen as a replacement for artists and animators.

According to Meta, the model allows users to create custom videos up to 16 seconds long and embed clips based on personal photos through simple text prompts. “Our model achieves cutting-edge results in creating personalized videos that preserve human identity and movement,” the company said.

Imagining possible applications, Meta suggested that users could create a “day in the life” video and share it on Reels, or design a custom animated birthday greeting to send via WhatsApp.

Movie Gen marks the third phase of AI-powered video generation at Meta and highlights the company's ongoing efforts in this area. However, the emergence of AI-generated tools to create realistic videos has raised concerns about the potential misuse of “deepfakes,” where people's likeness could be exploited without consent.