OpenAI releases text-to-video model Sora

OpenAI has launched Sora, it’s much awaited text-to-video generation model capable of creating videos from text prompts. The model allows users to convert written descriptions into videos, which can be further customised using additional prompts.

Sora was initially made available in February this year to select filmmakers and artists as part of its early access programme. 

According to the company, the model is capable of generating complex scenes with multiple characters, specific types of motion, with details of the subject and the background. It can understand not only what is asked in the prompt but also how it exists in the physical world, the company states.  

“One of the most exciting things to me about this product is how easy it is to co-create with others; it feels like an interesting new thing! This is early--think of it like GPT-1 for video--but I already think the feed is so compelling,” said Sam Altman, CEO of OpenAI, in a post on X. 

The product is designed to support video production across various industries by simplifying the creation process.

The Microsoft-backed firm is now entering the video-generation AI space, competing against some of its biggest tech rivals such as Google and Meta. Other competitors in the field include Stability AI, whose product Stable Diffusion is known for photorealistic image generation from text and image prompts. 

Sora's launch comes shortly after the introduction of a ChatGPT Pro subscription for $200 per month and the full release of OpenAI's o1 model with reasoning capabilities.