OpenAI releases Sora, its buzzy AI video-generation tool
OpenAI said Monday it’s releasing its buzzy AI video-generation tool, Sora, later in the day.
OpenAI said Monday it’s releasing its buzzy AI video-generation tool, Sora, later in the day.
The AI video-generation model works similarly to OpenAI’s image-generation AI tool, DALL-E: A user types out a desired scene, and Sora will return a high-definition video clip. Sora can also generate video clips inspired by still images and extend existing videos or fill in missing frames. The Microsoft-backed artificial intelligence startup, which burst into the mainstream last year thanks to the viral popularity of ChatGPT, introduced Sora in February.
It’ll debut to U.S. users as well as to “most countries internationally” later today, according to OpenAI’s YouTube livestream, and the company has “no timeline” yet for launching the tool in Europe and the U.K., as well as some other countries.
OpenAI said users don’t need to pay extra for the tool, which will be included in existing ChatGPT accounts such as Plus and Pro. Employees on the livestream and OpenAI CEO Sam Altman demonstrated features like “Blend” (i.e., joining two scenes together at the user’s direction), as well as the option to make an AI-generated video endlessly repeat.
Until now, Sora has mainly been available to a small group of safety testers, or “red-teamers,” who test the model for vulnerabilities in areas such as misinformation and bias.
Rating: 5