Skip to main content
POST

Authorization

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

Request Parameters

model
string
required
Video generation model nameSupported models:
  • kling-v3 - Kling v3 (recommended)
prompt
string
required
Text promptDescribe scenes, actions, styles in detail for better generation results. English prompts are recommended.Example: "a golden retriever running on the beach, sunset, cinematic"
negative_prompt
string
Negative prompt to exclude unwanted contentExample: "blurry, low quality, distorted"
mode
string
default:"std"
Generation modeOptions:
  • std - Standard mode (720P)
  • pro - Professional mode (1080P)
  • 4k - 4K mode
Default: std
duration
integer
default:"5"
Default: 5 Video duration (seconds)Range: 3-15 (minimum 3 seconds, maximum 15 seconds)⚠️ Note: Must be a plain number (e.g. 6), do not add quotes, otherwise an error will occur
aspect_ratio
string
default:"16:9"
Video aspect ratioOptions:
  • 16:9 - Landscape
  • 9:16 - Portrait
  • 1:1 - Square
Default: 16:9
image_urls
array<url>
Image URL array for image-to-video generation
  • Pass 1 image: used as first frame
  • Pass 2 images: automatically assigned as first frame + last frame
Maximum 2 images supportedExample: ["https://example.com/first.jpg"]
  • Maximum 2 images supported
  • Image URLs must be publicly accessible without hotlink protection
  • In image-to-video mode, aspect_ratio may be overridden by the actual image ratio
watermark
boolean
Whether to add watermark
audio
boolean
default:"false"
Whether to generate video with audio
multi_shot
boolean
default:"false"
Whether to enable multi-shot mode.
  • true
  • false
shot_type
string
Shot split method: customize / intelligence.Required when multi_shot=true.
multi_prompt
array<object>
Per-shot information, such as prompt and duration.Define shot order, prompt, and duration via index, prompt, and duration.
  • Supports 1 to 6 shots
  • Maximum content length per shot is 512
  • Each shot duration must be >= 1 and cannot exceed total task duration
  • Sum of all shot durations must equal top-level duration
Format:
Required when multi_shot=true and shot_type=customize.
element_list
array<object>
Reference subject list, up to 3 subjects.
  • Create on the fly via name, description, element_input_urls
Example:
Notes:
  • name, description, and element_input_urls are required for on-the-fly creation
  • element_input_urls: 2-4 images per subject (first as frontal image, rest as references)
  • Reference elements in prompt with @name, e.g. "@element_dog chasing @element_cat on grass"

Parameter Constraints

  • mode=4k is supported for kling-v3
  • image_urls supports up to 2 images (1 first frame, 2 first+last frames)
  • Last-frame-only input is invalid (must include first frame)
  • When multi_shot=true, top-level prompt can be omitted
  • multi_prompt supports up to 6 shots, and index must start from 1 and be continuous

Feature Support Matrix

Text-to-Video vs Image-to-Video

The system automatically determines the mode based on whether image_urls is provided: no images means text-to-video, with images means image-to-video.

Response

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

Use Cases

Case 1: Text-to-Video (Standard Mode)

Case 2: Text-to-Video (Pro Mode + Negative Prompt)

Case 3: Text-to-Video (15 seconds)

Case 4: Image-to-Video (First Frame)

Case 5: Image-to-Video (First + Last Frame Control)

Case 6: Generate Video with Audio

Case 7: Multi-Shot Storyboard (customize, 15 seconds, portrait with audio)

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