mingyanmingyan
wechatwechat
mingyan

Sora - Create Task

Create video generation tasks using Sora models with support for 4, 8, and 12 second durations and multiple resolutions

POST/kyyReactApiServer/v1/sora/videos

Sora Create Video Task

Create high-quality video generation tasks using Sora's advanced AI models. Current duration options are 4, 8, and 12 seconds.

Authentication

Get Key
All requests require a Bearer token in the request header:
cURL
Authorization: Bearer {{key}}

Base URL

https://zcbservice.aizfw.cn/kyyReactApiServer
baseUrl is the shared prefix for all public APIs. The api field in the current page frontmatter shows the full endpoint. Use this baseUrl as the common prefix when reading or composing request paths.

Request Parameters

modelstringrequired
Model name, available options:
  • openAiSora2Plus - Supports 4, 8, 12 seconds
  • openAiSora2Pro - Supports 4, 8, 12 seconds
promptstringrequired
Video generation prompt describing the desired video content
Example: "A cat dancing in the rain, cinematic style"
sizestring
Video dimensions, defaults to 720x1280
Available options:
  • 720x1280 - Portrait
  • 1280x720 - Landscape
Use either this or aspect_ratio, not both
aspect_ratiostring
Video aspect ratio
Available options:
  • 16:9 - Landscape
  • 9:16 - Portrait
Use either this or size, not both
durationinteger
Video duration in seconds. Supported values: 4, 8, 12
Use either this or seconds, not both
secondsinteger
Video duration in seconds. Supported values: 4, 8, 12
Use either this or duration, not both
input_referencearray
Reference image array to guide video generation, supports up to 1 images
Important Notes:
  • Do not upload real portrait images, as they are likely to fail
  • For openAiSora2-xxx series models, image format must match the ratio
  • Only supports 1280×720 (16:9 landscape) and 720×1280 (9:16 portrait)
Use either this or image_urls, not both
image_urlsarray
Reference image URL array to guide video generation
Important Notes:
  • Do not upload real portrait images, as they are likely to fail
  • For openAiSora2-xxx series models, image format must match the ratio
  • Only supports 1280×720 (16:9 landscape) and 720×1280 (9:16 portrait)
Use either this or input_reference, not both

Response Parameters

idstring
Unique identifier for the video generation task, used for subsequent status queries
objectstring
Object type, always video.generation
createdinteger
Task creation timestamp
modelstring
Model name used
statusstring
Task status:
  • queued - Queued
  • processing - Processing
errorstring
Error message, returned when status is failed

Model Features

openAiSora2Plus

OpenAI Sora2 Plus version, supports 4, 8, 12 seconds, enhanced model

openAiSora2Pro

OpenAI Sora2 Pro version, supports 4, 8, 12 seconds for higher-quality generation

Parameter Selection Rules

Mutually Exclusive Parameters:
  • Size parameters: Choose either size or aspect_ratio
  • Duration parameters: Choose either duration or seconds
  • Reference images: Choose either input_reference or image_urls

Video Duration Support

ModelSupported Durations
openAiSora2Plus4 seconds, 8 seconds, 12 seconds
openAiSora2Pro4 seconds, 8 seconds, 12 seconds
Best Practices:
  1. Video generation is asynchronous, use the returned id to query task status and results
  2. Clearly describe desired visual effects and style in the prompt
  3. Reference images can guide overall style, supports up to 1 images
  4. Choose appropriate aspect ratio to match your use case
Prompt Suggestions:
  • Include specific scene descriptions
  • Add style keywords (e.g., "cinematic", "artistic", "realistic")
  • Describe actions and movement patterns
  • Specify lighting and color preferences