OpenAI Delivers Sora AI Video Generator

Spurred no doubt by the recent preview of Google “Veo”, OpenAI today took its Sora generative AI video creation tool out of preview.

“Our Sora⁠ video generation model can create realistic videos from text,” the OpenAI announcement notes. “Sora serves as a foundation for AI that understands and simulates reality—an important step towards developing models that can interact with the physical world.”

Sora caused quite a stir when it was first announced back in February, but OpenAI says it’s even more impressive now, and there’s a new Sora Turbo version that is dramatically faster. It can generate Full HD (1080p) resolution videos up to 20 seconds in length, in widescreen, vertical or square aspect ratios using a prompt or your own assets. And there’s a new storyboard tool so you can specify inputs for each frame.

Sora is available now as a standalone offering to ChatGPT Plus and Pro users. Plus users can generate up to 50 videos at 480p resolution or fewer videos at 720p each month, while Pro users get 10 times more usage, higher resolutions, and longer video durations. More plans will be made available next year.

You can learn more on the Sora website.