OpenAI Sora-2
Version: 2025-10-06
Sora-2 builds upon Sora; it delivers advanced world simulation, realistic video generation, and synchronized audio (supports most major languages), with enhanced creative controls. It’s designed for production workflows across marketing, e‑commerce, entertainment, and education.
Unlike Sora, Sora-2 generates audio and includes the ability to edit generated videos.
Unlike Sora, Sora-2 generates audio and includes the ability to edit generated videos.
Key Capabilities
- Text to video generation
- Image to video generation
- Remixing: edit generated videos
- Realistic Video Generation: Powered by advanced simulation and physics for lifelike results.
- Synchronized Audio: Supports most major languages for immersive storytelling.
- Audio availability: available in the majority of languages.
- Seamless Integration: Designed for marketing, e‑commerce, entertainment, and education use cases.
Model provider
This model is provided through the Azure OpenAI Service.Relevant documents
The following documents are applicable:- Concepts of Video Generation
- Video Generation Quickstart
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/latest
- Overview of Responsible AI practices for Azure OpenAI models
- Transparency Note for Azure OpenAI Service
Video API
Provides 5 endpoints, each with distinct capabilities.- Create Video: Start a new render job from a prompt, with optional reference inputs or a remix id.
- Get Video Status: Retrieve the current state of a render job and monitor its progress
- Download Video: Fetch the finished MP4 once the job is completed.
- List Videos: Enumerate your videos with pagination for history, dashboards, or housekeeping.
- Delete Videos: Delete an individual video id from OpenAI’s storage
Access
The access to Sora-2 API is gated at launch. Enterprise (MCA-E and EA) customers and 1000+CU customers can apply for access via Sora-2 access application form .Sora is available via API and playground.
Safety
OpenAI has incorporated additional safety measures into Sora-2:- Only content suitable for audiences under 18. In the future there will be a setting to allow >18 content.
- Copyrighted characters and copyrighted music will be rejected.
- Real people (including public figures) cannot be generated.
Model Specifications
LicenseCustom
Last UpdatedOctober 2025
Input TypeText,Image,Video
Output TypeVideo,Audio
PublisherOpenAI
Languages1 Language