OpenAI launches Sora Turbo

Sora.com is rolling out a video generation model, OpenAI announced in a blogpost.

Earlier this year, OpenAI introduced Sora⁠, its model that can create realistic videos from text, and shared its initial research progress⁠ on world simulation. Sora serves as a foundation for AI that understands and simulates reality—an important step towards developing models that can interact with the physical world.

Today it is releasing Sora Turbo as a standalone product at Sora.com to ChatGPT Plus and Pro users. The new version of Sora is significantly faster than the model previewed in February. 

A new interface just for Sora

It is releasing a wide range of features⁠. Users can generate videos up to 1080p resolution, up to 20 sec long, and in widescreen, vertical or square aspect ratios. One can bring its own assets to extend, remix, and blend, or generate entirely new content from text.

It has developed new interfaces to make it easier to prompt Sora with text, images and videos. Its storyboard tool lets users precisely specify inputs for each frame.

It also has Featured and Recent feeds that are constantly updated with creations from the community.

Sora availability and subscriptions
Sora is included as part of the Plus account at no additional cost. One can generate up to 50 videos at 480p resolution or fewer videos at 720p each month.

The Pro plan includes 10x more usage, higher resolutions, and longer durations. OpenAI is working on tailored pricing for different types of users, which it plans to make available early next year.

OpenAI's approach to deployment

The version of Sora has many limitations. It often generates unrealistic physics and struggles with complex actions over long durations. Although Sora Turbo is much faster than the February preview, it is still working to make the technology affordable for everyone.

It is introducing the video generation technology now to give society time to explore its possibilities and co-develop norms and safeguards that ensure it’s used responsibly as the field advances. 

All Sora-generated videos come with C2PA metadata, which will identify a video as coming from Sora to provide transparency, and can be used to verify origin. While imperfect, it has added safeguards like visible watermarks by default, and built an internal search tool that uses technical attributes of generations to help verify if content came from Sora.

Today, it is blocking particularly damaging forms of abuse, such as child sexual abuse materials and sexual deepfakes. Uploads of people will be limited at launch, but it intends to roll the feature out to more users as it refines its deepfake mitigations.