Skip to main content
POST
Note for users in mainland China: Please use https://toapis.cn as the API endpoint (Base URL). Replace https://toapis.com with https://toapis.cn in the examples in this document.
  • ByteDance Doubao video generation model 1.5 Pro version
  • Supports text-to-video generation
  • Supports first frame / last frame control
  • Does not support reference image mode
  • Supports audio generation (1.5 Pro exclusive feature)
  • 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
default:"doubao-seedance-1-5-pro"
required
Video generation model nameAvailable models:
  • doubao-seedance-1-5-pro - 1.5 Pro version, supports audio generation and first/last frame control
string
required
Video content descriptionDescribe scenes, actions, and style in detail for better generation resultsExample: "Sunset at the beach, golden sunlight on the sea, waves gently hitting the sand"
integer
default:5
Video duration (seconds)Supported range: 4 ~ 12 secondsDefault: 5
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 and Aspect Ratio Combinations

string[]
Compatibility image URL array for first/last-frame image-to-video generationCompatibility rules:
  • 1 image: treated as first_frame
  • 2 images: treated as first_frame and last_frame
  • More than 2 images: only the first two are used
We recommend using image_with_roles to explicitly specify first and last framesExample: ["https://example.com/first.png", "https://example.com/last.png"]image_urls and image_with_roles cannot be used together
array
Image array with roles for explicit first/last-frame controlExample:
  • image_urls and image_with_roles cannot be used together
  • Only one first frame and one last frame are supported
  • 1.5 Pro does not support the reference_image role. Use Seedance 2.0 if you need reference image control
object
Extended parameters

Differences from 1.0

Asset review

When a request includes images, some channels review them automatically before submitting generation. No extra parameter is needed; pass image URLs in the existing image fields.
  • An accepted request returns a video task immediately. When review is required, the task stays queued and generation is submitted only after all media in the request pass. First-time review can take several minutes; reusing the same URL for the same user and channel reuses the review result.
  • Each media preparation round lasts up to 20 minutes by default. Rejection or preparation timeout ends the task as failed; see error.message for the reason. Failed review incurs no video generation fee.
  • Images must be public HTTP(S) URLs; Base64 and local paths are not accepted. Keep images within 20 MB (some channels allow up to 30 MB). The model’s existing format limits still apply.
  • Channels that review media validate image URLs at submission: a URL with embedded credentials or longer than 2048 bytes returns HTTP 400 with error.code invalid_private_assets.
  • Media is identified by URL. Use a new URL after the file content changes.
  • Legacy asset:// references are retired and return HTTP 400.

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