Say hello to Sora: OpenAI’s new text-to-video tool

OpenAI has officially launched Sora, its news text-to-video generator, offering users an innovative way to create short, lifelike video clips from written prompts, Kazinform News Agency reports.

Sora is a tool that creates short, realistic video clips out of written instructions. Users can also combine or extend material by including their own media files.

“We hope this early version of Sora will enable people everywhere to explore new forms of creativity, tell their stories, and push the boundaries of what’s possible with video storytelling,” OpenAI wrote in a blog post.

In a video presentation, the company demonstrated Sora’s capabilities that for now are limited to “videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.”

But Sora's present form has restrictions. The model finds difficult actions, long-duration videos, and creating reasonable physics challenging. OpenAI has taken precautions and put visible watermarks and metadata to confirm authenticity among other protections. Limitations on uploads including individuals remain in place to stop abuse, including the generation of damaging deepfakes.

“We’ll be taking several important safety steps ahead of making Sora available in OpenAI’s products. We are working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who are adversarially testing the model,” the company said.

Sora will initially be available to ChatGPT Plus and Pro subscribers in the U.S. and most international markets, though it will not launch in the U.K. or Europe.

First unveiled in February to a small group of artists, filmmakers, and safety testers, Sora is OpenAI's most recent addition. Famous for its popular ChatGPT chatbot, the company is currently valued at around $160 billion.