Skip to main content
POST
Pricing: See vibetool.ai/pricing for current rates.
Seedance 2.0 produces videos asynchronously. The creation endpoint returns a task_id. Use the Get Video Result endpoint to poll for completion.

Authorization

string
required
All API requests require Bearer Token authentication. Provide your key as Bearer YOUR_API_KEY.

Request Body

string
required
The model ID. Always use "seedance-2.0-image-to-video".
string
required
The input image URL or a base64-encoded data URI. Must be in JPEG or PNG format.
string
required
A text description of the desired video content. Maximum 1000 characters.
string
Text describing what to avoid in the generated video.
number
Desired video duration in seconds. Supported range depends on the plan. Defaults to 4 seconds if not specified.
boolean
Whether to apply enhancement post-processing. Defaults to false.

Response Body

string
required
Unique identifier for the generation task. Use this to poll for results.
enum<string>
required
Initial task status. Always "pending" immediately after creation.
Possible values: pending, processing, completed, failed.
integer | string
required
Unix timestamp (seconds) when the task was created.

Request Examples

Response Examples

Get Video Result

Once a task is created, poll its status with: GET https://api.vibetool.ai/v1/videos/status/{task_id} The response includes progress, video_url (when completed), and error (on failure). See the Get Video Result reference for full details.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
enum<string>
required

Use seedance-2.0-image-to-video.

Available options:
seedance-2.0-image-to-video
image
string<uri>
required

Input image used as the starting frame

prompt
string
required

Text description of the video to generate

negative_prompt
string

Content to avoid in the generated video

duration
number

Duration in seconds

enhance
boolean

Enable prompt enhancement

Response

Task created

id
string

Unique identifier for the generation task

object
string
Example:

"video.generation"

model
string
created_at
integer

Unix timestamp (seconds)

status
enum<string>

Initial task status

Available options:
pending,
processing
task_id
string

Task ID for the status polling endpoint