Describing a scene and watching it come to life as a video — that's what OpenAI Sora makes possible. It's a text-to-video model that can generate videos up to a minute long while maintaining impressive visual quality and faithfully following the user's text instructions. It's designed to serve as a foundation for AI models that can truly understand and simulate the physical world.
The ambition goes beyond just creating videos — OpenAI envisions Sora helping people solve real-world problems that require understanding physical interaction and cause-and-effect. Currently, access is limited to red teamers, safety testers, and select visual artists, designers, and filmmakers, as OpenAI gathers feedback before a wider release.
Subscribe to get the latest OpenAI Sora and global AI updates.
