OpenAI previews Sora, a text-to-video model

OpenAI previewed Sora on 15 February 2024, a model that generates up to a minute of high-definition video from a text prompt. Access went first to red-teamers and a group of visual artists; a standalone product followed in December 2024.

Why it mattered The realism of the sample clips widened the argument over synthetic video’s effect on misinformation and visual-effects work, months before anyone outside OpenAI could use it.