Home / Technology / OpenAI Unveils Sora 2: The Next-Gen AI Video Generator
OpenAI Unveils Sora 2: The Next-Gen AI Video Generator
30 Sep
Summary
- OpenAI releases Sora 2, an advanced audio and video generator
- Sora 2 improves on physics realism compared to prior models
- OpenAI also launches Sora, a social app for sharing AI-generated videos
Last month, on October 1st, 2025, OpenAI unveiled Sora 2, the latest iteration of its AI-powered audio and video generation technology. Sora 2 builds upon the capabilities of the original Sora model released a year earlier, with a focus on improving the realism of the generated content.
According to OpenAI, Sora 2 is better at adhering to the laws of physics, ensuring that objects and movements in the videos appear more natural and lifelike. The company has shared impressive examples showcasing Sora 2's abilities, including scenes of beach volleyball, skateboarding tricks, gymnastics routines, and cannonball jumps.
Alongside the Sora 2 model, OpenAI has also launched a new social platform called Sora, where users can generate and share their own AI-powered videos. The app includes a "cameos" feature that allows users to insert their own likeness into the generated scenes, and even share that ability with their friends.
OpenAI believes that the Sora social app is the best way for people to experience the capabilities of Sora 2. The app is currently available in the U.S. and Canada, with plans to expand to other countries in the near future. While the Sora platform is invite-only, users of OpenAI's ChatGPT Pro service will be able to access the Sora 2 Pro model without an invitation.
