OpenAI's Sora is a breakthrough new tool that turns text into videos: Here's how it works

OpenAI's Sora is the new disruptor.

The breakthrough new tool by the ChatGPT maker allows users to create realistic artificial intelligence videos using just text prompts and photos.

OpenAI's Sora, which means sky in Japanese, can produce realistic videos of up to a minute after taking instructions from a user on the style and subject of the clip.

What's new in OpenAI's Sora?

The artificial intelligence company, helmed by Sam Altman, in a blog post said Sora also has the ability to generate realistic videos using still images or existing footage provided by the user for reference.

“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,” said OpenAI in the post.

Read more: OpenAI's Sam Altman to raise ‘trillions of dollars’ to ‘reshape’ semiconductor industry: Report

One of the example prompts displayed by OpenAI was “a movie trailer featuring the adventures of the 30-year-old space man wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, vivid colors.”

How can you access OpenAI's Sora?

The access to Sora has been opened for a researchers and content curators to make sure that the new AI model is adhering to the security policies of OpenAI, which prohibit “extreme violence, sexual content, hateful imagery, celebrity likeness, or the IP of others," the blogpost said.

After Sora's launch, Sam Altman also took to X (formerly Twitter) and replied to a few users with videos based on their prompts. The videos contain a watermark which shows that the clip is make by AI.

Read more: OpenAI's Sam Altman seeks to raise billions for artificial intelligence chip factories venture

Google and Meta have also tried to invest in AI technology similar to Sora, but OpenAI has taken it one step further with hyper-realistic videos based on just text prompts.

Sora is not available for public usage yet and OpenAI has released little information about how it actually works and how the model was created.

The new AI software is only available for red teaming, which will help the company detect any flaws in its development.

Meanwhile, OpenAI is also working on tools that can discern if a video was developed by AI.