Text-to-video generation from OpenAI, reached through ChatGPT and a storyboard app
Sora is OpenAI's video generation model, exposed both inside ChatGPT and through a separate web app for short clips. You describe a scene, optionally upload a still to animate, and the model returns a few seconds of moving footage, sometimes with sound. It handles multi-subject scenes, camera movement and continuity between shots better than most early competitors, and the storyboard view lets you lay out several shots before generating them so a sequence holds together. Access is gated by plan and region rather than by anything technical, and that gating is the main practical limit for most people.
Last updated: 2026-09-20. This site only provides an index; for exact features, pricing, and licensing, see the official website.
concept shots, storyboards, short cinematic clips and social video tests
If you're comparing similar products, check the alternatives below, or browse all tools in the AI Video Creation category.
In practice yes. Sora ships through ChatGPT plans rather than as a separate purchase, so an eligible paid plan and a supported region are both required. Availability for free users has varied by market, so check the current plan page.
The model can produce clips with audio, including speech and ambient sound, and the team has kept expanding that. Quality varies by scene, and plenty of people still add music and sound design in an editor afterwards.
Clips are measured in seconds rather than minutes, and available lengths depend on the current model version and your plan. Longer pieces are built by extending a clip or arranging several shots in the storyboard instead of asking for one long take.
Professional video editor with transcript-based editing and speech cleanup
Editing, colour, audio and visual effects in one app, free in its full form
Google's hosted model that generates video with sound from a text prompt
AI video generation and editing suite for filmmakers