Meta has launched Movie Gen, a generative AI tool designed for video and audio production that represents the company’s third phase in generative AI research, following models like Make-A-Scene and Llama Image.

The tool enables four key functions: video generation, personalized video creation, editing, and audio generation.

It leverages a transformer model with 30 billion parameters, capable of producing high-definition videos lasting up to 16 seconds at 16 frames per second.

Additionally, a 13 billion parameter audio generation model produces high-quality, synchronized sound to accompany both generated and edited video content.