S
Sora ✓ Verified
OpenAI's text-to-video AI model — generates photorealistic videos from text descriptions
About Sora
Sora is OpenAI's text-to-video generation model that creates photorealistic videos up to 60 seconds from text prompts. It understands physical world dynamics, camera movement, and cinematic composition. Note: As of March 2026, OpenAI announced the shutdown of the standalone Sora app, integrating video capabilities directly into ChatGPT.
Key Features
✓ Text-to-video with photorealistic quality
✓ Up to 60-second video generation
✓ Understands physics, motion, and 3D consistency
✓ Multiple aspect ratios and resolutions
✓ Image-to-video and video-to-video capabilities
✓ Integrated into ChatGPT on Pro plan ($200/mo)
✓ Cinematic camera movements and compositions
✓ Character and scene consistency across frames
✓ Storyboard mode for multi-shot sequences
✓ One of the most capable video generation models
Who Is It For?
Creative professionals, filmmakers, and ChatGPT Pro subscribers who need AI-generated video content.