Sora

OpenAI’s Sora is a groundbreaking text-to-video AI model that can create realistic and imaginative videos from text prompts. It’s designed to generate videos up to a minute long, maintaining visual quality and adhering closely to the user’s input.

Sora can create complex scenes involving multiple characters, specific motions, and detailed backgrounds, showcasing an impressive understanding of how elements exist in the physical world. The prompts can range from simple scenarios to elaborate, fantastical settings, demonstrating Sora’s versatility and creative potential.

Sora: Creating video from text

We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction.