Skip to main content
POST

Authorization

string
required
All API endpoints require Bearer Token authenticationGet your API Key:Visit the API Key Management Page to get your API KeyAdd to the request header:

Request Parameters

string
required
Video generation model nameAvailable models:
  • veo3.1-fast-official - Veo 3.1 Official Fast version
  • veo3.1-quality-official - Veo 3.1 Official High Quality version
string
required
Positive text promptDescribe scenes, actions, styles, etc. in detail for better generation results. English prompts are recommended.Example: "a golden retriever running on the beach, sunset, cinematic"
string
Negative prompt to exclude unwanted contentExample: "blurry, low quality, watermark, text"
integer
default:"8"
Video duration in secondsRecommended values: 4 / 6 / 8Default: 8Note: Must be a pure number (e.g. 8), do not add quotes, otherwise an error will occur
string
default:"16:9"
Video aspect ratioAvailable values:
  • 16:9 - Landscape
  • 9:16 - Portrait
Default: 16:9
string
default:"720p"
Video resolutionAvailable values:
  • 720p - Standard resolution
  • 1080p - High definition
  • 4K - Ultra high definition
Default: 720p
string
First frame image URL for image-to-video generation
  • Image URL must be publicly accessible without hotlink protection
  • Object storage URLs are recommended over temporary download links
string
Last frame image URL for image-to-video generationUsed with first_frame_image to control first and last frames
integer
Random seed for reproducing generation resultsValue range: 0 - 4294967295
integer
default:"1"
Number of samples to generate (1-4), currently recommended to use 1Default: 1
boolean
default:"false"
Whether to generate audio track
string
default:"allow_adult"
Person generation policyAvailable values:
  • allow_adult - Only allow generating adult persons/faces
  • disallow - Do not allow generating persons or faces
Default: allow_adult
string
default:"pad"
Image resize strategy (effective for image-to-video)Available values:
  • pad - Padding mode
  • crop - Cropping mode
Default: pad
boolean
default:"true"
Whether to enable upstream prompt enhancementDefault: true
  • This parameter can only be set to true. Setting it to false will cause a request error
  • If you don’t need this parameter, do not include it

Text-to-Video vs Image-to-Video

The system automatically determines the mode based on whether image parameters are provided: no images for text-to-video, images for image-to-video.

Response

integer
Response status code, 200 on success
array
Response data array

Usage Scenarios

Scenario 1: Text-to-Video (Basic)

Scenario 2: Text-to-Video (Full Parameters)

Scenario 3: Image-to-Video (Single First Frame)

Scenario 4: Image-to-Video (First Frame + Last Frame)

Scenario 5: Video with Audio

Query Task ResultsVideo generation is an asynchronous task that returns a task_id upon submission. Use the Get Task Status endpoint to query generation progress and results.