Skip to content

Sora

← All terms · Image, video, audio AI

Also called Sora 2

A text-to-video model developed by OpenAI, capable of generating highly realistic, extended video scenes that accurately simulate physical world dynamics.

What it is

Sora changed the landscape of AI video by demonstrating an understanding of how objects interact in the physical world. Using a diffusion transformer architecture, it can generate complex camera motions, consistent characters, and long-duration clips from simple text instructions, serving as a capable tool for filmmakers and creators.

When you would use it

You reach for Sora when you need leading, highly realistic AI video generation with strong adherence to real-world physics and complex camera motion.

Common operations

  • Generating cinematic b-roll footage and establishing shots.
  • Prototyping highly realistic visual effects and camera fly-throughs.

Related terms

Where this is taught

No learning path uses this term yet. Browse the Learning Atlas for guided sequences through related ideas.

Going deeper