Skip to main content
POST
Pricing: See vibetool.ai/pricing for current rates.Video generation is asynchronous. After submitting a prompt, you’ll receive a task_id to poll for the result.

About

Seedance 2.0 is ByteDance’s second-generation video model for multimodal video generation, now with full real human video support. Available globally with per-second billing and accessible through Vibetool’s OpenAI-compatible API.
  • Input: Text prompt
  • Output: Video (MP4)
  • Max resolution: 1080p (depending on parameters)

Endpoint

Authorization

string
required
All APIs require Bearer Token authentication. Format: Bearer YOUR_API_KEY

Request Body

string
required
Model identifier. Use seedance-2.0-fast-text-to-video.
string
required
Text description of the video to generate. Maximum 2048 characters.
string
A description of what to avoid in the generated video. Optional, up to 1024 characters.
integer
default:"4"
Video duration in seconds. Supported values: 2, 4, or 8.
string
default:"1920x1080"
Output resolution. Supported: 1920x1080, 1080x1920, 1024x1024, 720x720.
integer
Optional seed for deterministic generation. If provided, same seed + prompt yields the same video.

Response Schema (Creation)

string
required
Unique task ID. Use this to poll for the result (format: vid_...).
string
required
Always video.generate.
string
required
The model used, seedance-2.0-fast-text-to-video.
integer
required
Unix timestamp (seconds) of task creation.
string
required
Alias for id. Same value.
string
required
Initial status: pending.

Polling for Results

After receiving the task ID, poll the Get Video Result endpoint with:
The response includes a video_url field when status is completed.

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-fast-text-to-video.

Available options:
seedance-2.0-fast-text-to-video
prompt
string
required

Text description of the video to generate

negative_prompt
string

Content to avoid in the generated video

duration
integer
default:4

Duration in seconds

size
string
default:1920x1080

Output resolution

seed
integer

Random seed for reproducibility

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