OpenAI has unveiled a new artificial intelligence (AI) system that can create realistic-looking videos based on text prompts from users, making it the latest company in the tech space to embrace generative video technology. The system, called Sora, can quickly create videos up to a minute long that represent “complex scenes with multiple characters, specific types of movement, and precise details of objects and backgrounds”, the company says.
The tool will initially be made available to “a limited number of creators”, OpenAI CEO Sam Altman wrote in a post on social platform X.
OpenAI also provides access to a team of experts tasked with evaluating Sora’s safety before making it widely available.
Meta Platforms Inc, Alphabet Inc’s Google. and Runway AI have already created text-to-video generators. While this technology can speed up the creative process, it can also heighten concerns about AI interfering with artists’ livelihoods and spreading misinformation, especially in a key election year.
As part of its preparations for the product release, OpenAI says it is building tools to help detect when a video is generated by Sora. But companies in this field have tried before without success to create reliable systems to detect such videos. Last year, OpenAI abandoned a classifier that was designed to detect AI-generated text, citing its “low accuracy rate”.
