Video generation
Also called AI video, text-to-video, AI video generator
Making short video clips, often with sound, from a text description or a still image, using an AI model.
Video models do what image models do, across time: each frame has to look right and also follow on from the one before, so a person keeps the same face and a ball falls the way balls fall. The newest models generate the soundtrack too, so a clip of a café comes with the clatter of cups.
Clips are short, usually seconds, and the best results come from describing one shot the way a director would: who's in it, what moves, where the camera is, what the light is like.
It's also the most expensive thing a consumer AI app does, which is why it sits behind paid plans and tight limits, and why OpenAI closed its Sora video app in 2026 to spend its computing power on other work.
For example
A baker turns one photo of a cake into an eight-second clip of it being sliced, for an Instagram post.
Put it to use
Where you'll meet video generation in ChatGPT, Gemini and Claude, how to use it there, and the mix-up most people make.
Daily Bytes Plus is in the Android app.