sora
sora
Version: 2025-05-02
OpenAILast updated May 2025
An efficient AI solution to generate videos
Multimodal
Sora generates videos from text prompts that are provided by the user (with image to video coming soon). It generates videos up to 20s in duration and 1080p resolution.
Sora focuses on generating commercially safe content, ideal for customers in advertising, media, and entertainment. It can also be used to create onboarding videos for various enterprises.
  • Model input: text
  • Model output: video

Model provider

This model is provided through the Azure OpenAI service.

Relevant documents

The following documents are applicable:

Responsible AI Considerations

Sora has safety built-in by design across modalities, including additional safety measures such as provenance. This is crucial for transparency and accountability, ensuring
that the data used is accurate and free from bias.
Model Specifications
LicenseCustom
Last UpdatedMay 2025
Input TypeText
Output TypeVideo
PublisherOpenAI
Languages1 Language