Sora
OpenAIOpenAI's video model: text or image in, short clip out, with storyboard control.
Google DeepMind's video model, available through Gemini and Vertex AI.
Generating a clip with a described camera move and consistent subject from a start frame
Teams that need a simple per-clip API without a cloud project and billing setup
A video generation model that accepts text, image, or a reference frame and produces clips with audio in the newer versions. The distinguishing controls are camera and motion descriptions rather than the prompt alone. Access runs through Google’s products, so the practical gate is a billing-enabled project rather than a signup.
OpenAI's video model: text or image in, short clip out, with storyboard control.
Talking-head video without a camera, in dozens of languages.
Kuaishou's video generator, tuned for motion and image-to-video.
3 alternatives overlap with this one. Compare them →