An AI System to Transform Text Into Lifelike Videos is Unveiled by OpenAI

The latest artificial intelligence startup to embrace generative video technology is OpenAI, which teased a new system that can produce realistic-looking videos in response to text prompts from users.

The business stated in a blog post on Thursday that the AI system, known as Sora, can swiftly produce videos up to a minute long that depict «complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background.»

«A limited number of creators» will be the tool’s initial audience, according to a post on X by OpenAI Chief Executive Officer Sam Altman. Additionally, OpenAI is providing access to a group of professionals whose job it is to evaluate Sora’s security before integrating it into the company’s offerings.

Text-to-video generators had previously been developed by Meta Platforms Inc., Runway AI, and Google, a division of Alphabet Inc. Although this technology could expedite the creative process, it could also heighten worries about artificial intelligence (AI) upending the livelihoods of artists and disseminating false information, especially during a crucial election year.