Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedance-1-5-pro",
    "prompt": "A cute kitten playing in the sunlight, fluffy fur, bright eyes",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "audio": true
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01K8SGYNNNVBQTXNR4MM964S7K"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://gccai.heqingsong.uk/llms.txt

Use this file to discover all available pages before exploring further.

curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedance-1-5-pro",
    "prompt": "A cute kitten playing in the sunlight, fluffy fur, bright eyes",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "audio": true
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01K8SGYNNNVBQTXNR4MM964S7K"
    }
  ]
}

​
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:
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

​
model
string
required
Video generation model nameSupported models:
  • doubao-seedance-1-5-pro - 1.5 Pro version, supports audio generation and first/last frame
​
prompt
string
required
Video content descriptionDescribe scenes, actions, styles in detail for better generation resultsExample: "Sunset at the beach, golden sunlight on the sea, waves gently hitting the sand"
​
duration
integer
default:"5"
Video duration (seconds)Supported range: 4 ~ 12 secondsDefault: 5
​
aspect_ratio
string
default:"16:9"
Video aspect ratioOptions:
  • 16:9 - Landscape
  • 9:16 - Portrait
  • 1:1 - Square
  • 4:3 - Traditional ratio
  • 3:4 - Vertical traditional ratio
  • 21:9 - Ultra-wide
Default: 16:9
​
resolution
string
default:"720p"
Video resolutionOptions:
  • 480p - Standard definition
  • 720p - High definition
  • 1080p - Full HD
Default: 720p
​
seed
integer
Seed integer for controlling the randomness of generated contentValue range: Integer between -1 and 2^32-1
  • With the same request, if the model receives different seed values (e.g., not specifying seed or setting seed to -1, which will use a random number), different results will be generated
  • With the same request, if the model receives the same seed value, similar results will be generated, but not guaranteed to be identical
​
audio
boolean
default:"false"
Whether to generate audioWhen set to true, the video will include AI-generated accompanying audioDefault: false
Audio generation is exclusive to 1.5 Pro, the 1.0 version does not support this parameter
​
camerafixed
boolean
default:"false"
Whether to fix the cameraWhen set to true, the camera position remains fixedDefault: false

​
Resolution and Aspect Ratio Combinations

ResolutionSupported Aspect RatiosNotes
480p16:9, 4:3, 1:1, 3:4, 9:16, 21:9All supported
720p16:9, 4:3, 1:1, 3:4, 9:16, 21:9All supported
1080p16:9, 4:3, 1:1, 3:4, 9:16, 21:9All supported
​
image_urls
array<url>
Image URL array for image-to-video generationAuto role assignment rules:
  • 1 image = first frame
  • 2 images = first frame + last frame
Example: ["https://example.com/first.png", "https://example.com/last.png"]
  • image_urls and image_with_roles cannot be used together
​
image_with_roles
array
Image array with roles for more precise controlExample:
[
  {"url": "https://example.com/start.png", "role": "first_frame"},
  {"url": "https://example.com/end.png", "role": "last_frame"}
]
  • image_urls and image_with_roles cannot be used together
  • First frame and last frame only support one each

​
Response

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

​
Use Cases

​
Case 1: Text-to-Video with Audio

{
  "model": "doubao-seedance-1-5-pro",
  "prompt": "Sunset at the beach, golden sunlight on the sea, waves gently hitting the sand",
  "audio": true
}

​
Case 2: High-Quality Portrait Short Video

{
  "model": "doubao-seedance-1-5-pro",
  "prompt": "A girl spinning under cherry blossom trees, petals falling with the wind",
  "duration": 5,
  "aspect_ratio": "9:16",
  "resolution": "720p",
  "audio": true
}

​
Case 3: First Frame to Dynamic Video

{
  "model": "doubao-seedance-1-5-pro",
  "prompt": "Animate the image with natural dynamic effects",
  "image_urls": ["https://example.com/first.png"],
  "duration": 5,
  "audio": true
}

​
Case 4: Transition Effect with First/Last Frame

{
  "model": "doubao-seedance-1-5-pro",
  "prompt": "Scene transitions from day to night, city lights gradually turning on",
  "image_with_roles": [
    {"url": "https://example.com/day.png", "role": "first_frame"},
    {"url": "https://example.com/night.png", "role": "last_frame"}
  ],
  "duration": 5
}
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.

​
Differences from 1.0 Version

Feature1.0 fast/quality1.5 Pro
Default resolution1080p720p
Supported resolutions480p/720p/1080p480p/720p/1080p
Duration range2-12s4-12s
Audio generationNot supportedSupported
Reference imagereference (1 image)Not supported