Alexander Lewis
Feb 16, 2024
OpenAI revealed its development of a novel artificial intelligence (AI) model dubbed Sora AI on Thursday, designed to generate videos solely based on text inputs.
In a post shared on X, formerly known as Twitter, the company maintained that Sora, its new generative AI tool, can "create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions."
While citing sources familiar with the matter, Reuters said the company is "working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who are adversarially testing the model."
Read more: Text to video generator — OpenAI working on new AI model Sora
Is Sora AI available to use?
Is Sora AI currently accessible to everyone? Not at the moment. OpenAI has outlined plans to implement certain "safety steps" before integrating Sora into its products. Additionally, the company will collaborate with red teamers, and experts in fields such as misinformation, hateful content, and bias, who will rigorously test the model.
The generative AI tool has been built upon OpenAI's ChatGPT chatbot, which gained widespread acclaim upon its release in 2022 for its exceptional ability to craft poetry, emails, and software code.
According to the company's official blog post, Sora AI is still a work in progress. Currently, it struggles with accurately interpreting spatial details from prompts and faces challenges in adhering to user-requested camera trajectories.
