Meta Unveils New AI Model Capable of Generating Video with Sound, Challenging OpenAI

By Katie Paul

NEW YORK (Reuters) – Meta, the parent company of Facebook, announced on Friday the development of a new AI model known as Movie Gen. This innovative tool can generate realistic video and audio clips in response to user prompts, positioning itself as a competitor to prominent media generation startups such as OpenAI and ElevenLabs.

Meta showcased samples of Movie Gen’s capabilities, featuring videos of animals swimming and surfing, as well as clips using real photographs of individuals performing various actions like painting on a canvas.

In addition, Movie Gen is designed to produce background music and sound effects that are synchronized with the video content, as stated in a company blog post.

Moreover, the tool allows users to edit existing videos. In one illustrative example, Movie Gen was used to add pom-poms to a man’s hands while he was running in the desert. In another instance, it transformed a dry parking lot in a skateboard video into one that was splashed with water.