Skip to main content
POST
  • Azure Sora 2 video generation model (official Azure OpenAI endpoint)
  • Use model parameter to select sora-2-official
  • Supports text-to-video, image-to-video, and remix
  • Async task management, query results by task ID

Authorizations

string
required
All endpoints require Bearer Token authenticationGet your API Key from the API Key Management PageAdd to request header:

Body

string
required
Video generation model nameSupported models:
  • sora-2-official - Azure Sora 2 official model
Example: "sora-2-official"
string
required
Natural-language description for video generationInclude shot type, subject, action, setting, lighting, and camera motion to reduce ambiguity. Keep it single-purpose for best adherence.Example: "A golden retriever running on grass, sunny day"
integer
default:"4"
Video duration in secondsSupported values:
  • 4 - 4 seconds
  • 8 - 8 seconds
  • 12 - 12 seconds
Default: 4Example: 12
string
default:"9:16"
Video aspect ratioSupported formats:
  • 16:9 (Landscape, 1280×720)
  • 9:16 (Portrait, 720×1280)
Default: 9:16
string[]
Array of reference image URLs for image-to-video generation⚠️ URL format only
  • Publicly accessible image URL (http:// or https://)
  • You can use the Upload Image API to upload local images and get URLs
  • Only the first image will be used as reference
  • Supported formats: JPEG, PNG, WebP
  • Image size must be 1280×720 (16:9) or 720×1280 (9:16)

Response

string
Unique task identifier for status queries
string
Object type, always generation.task
string
Model name used
string
Task status
  • queued - Queued for processing
  • in_progress - Processing
  • completed - Successfully completed
  • failed - Failed
integer
Task progress percentage (0-100)
integer
Task creation timestamp (Unix timestamp)
object
Task metadata including size and duration