OpenAI Sora: What is it, is there a release date & how do you use the text-to-video generator?

OpenAI has announced a new artificial intelligence system called Sora, a text-to-video generator which is set to revolutionise how content is created in the modern age. Sora is the latest software from Sam Altman's OpenAI empire, which brought the public ChatGPT and Dall-E.

OpenAI was thrust into the global spotlight after ChatGPT was launched in 2022. The popular AI chatbox is used throughout the world by more than 100 million users per month.

Altman helped start OpenAI as a non-profit research laboratory in 2015, with financial backing from Tesla chief executive Elon Musk and others. Its stated aims were to “advance digital intelligence in the way that is most likely to benefit humanity as a whole, unconstrained by a need to generate financial return”.

But what is the company's brand new AI product, is there a release date for the software and how does it work? Here's everything you need to know.

What is Sora?

Sora is a new AI model from OpenAI - the company behind ChatGPT. The tool allows users to create life-like videos from text prompts, with a similar user experience to the company's text-to-image programme Dall-E.

According to OpenAI, Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt. The model is also able to build upon existing media by generating a video from a still image, or by extending and adding to videos which require extra frames.

"The model is able to take an existing still image and generate a video from it, animating the image’s contents with accuracy and attention to small detail," it further stated. Sora can also extend existing videos or fill in gaps by generating missing frames. 

How to use Sora OpenAI

Similar to Dall-E, users are required to write a prompt which can allow the programme to generate a video. Earlier this week, OpenAI cheif, Sam Altman, requested prompts from users on X - formerly Twitter - to test the programme.

One of the prompts reads: "A instructional cooking session for homemade gnocchi hosted by a grandmother social media influencer set in a rustic Tuscan country kitchen with cinematic lighting."

After the user has input their prompt, the AI model will create a video limited to one minute in length. However, users can create longer videos by adding seperate prompts and synchronising them with frame count.

Is there a release date for Sora OpenAI?

On Thursday (February 15) OpenAI confirmed Sora is now available to red teamers and a number of visual artists, designers, and filmmakers. This means Sora is still in its 'testing' phase with OpenAI looking to receive feedback on the safety and security of the model, along with its user experience.

It is currently unclear when the text-to-video generator will receive a widespread release to the public.