OpenAI unveils text-to-video model, Sora

By Ovunc Kutlu

ISTANBUL (AA) - US-based artificial intelligence (AI) research company OpenAI on Thursday unveiled its text-to-video AI model, named Sora.

"Sora is an AI model that can create realistic and imaginative scenes from text instructions," the company said in a statement. "We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction."

The company said Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.

OpenAI said it is granting Sora's access to a number of visual artists, designers and filmmakers in order to gain feedback on how to advance the model to be most helpful for creative professionals.