Skip to main content
POST
Pricing: See vibetool.ai/pricing for current rates.
Seedance 2.5 Video Edit is ByteDance’s latest video model. It generates 480p/720p video from a text prompt, and can edit or extend existing footage you supply as a video reference. Outputs run 4–30 seconds, include native audio, and are billed per second.

Input Modalities

  • Text — a prompt describing the desired edit, motion, or scene
  • Video — an existing clip to edit or extend (optional; omit it for pure text‑driven generation)

Output Modality

  • Video — an MP4 file at 480p or 720p, 4–30 seconds, with native audio

Authorization

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

Request Body

string
required
The model identifier. Use "seedance-2.5-video-edit".
string
A publicly accessible URL to an MP4 clip to edit or extend. When provided, the model uses the footage as its visual reference and applies the requested changes. Omit it to generate video from the text prompt alone.
string
Text description of the desired edit or generated content (e.g., “extend the clip, keep the subject’s motion, and soften the lighting”).
number
Requested video duration in seconds (defaults to 4, maximum 30). The model may adjust to match its capabilities.

Response Schema

string
required
Unique identifier for the generation task.
string
required
Type of object, always "video.generation".
string
required
The model used, e.g., "seedance-2.5-video-edit".
integer
required
Unix timestamp (seconds) of task creation.
string
required
Initial status: "pending" or "processing". Use the Get Video Status endpoint to poll for completion.
string
required
The task ID to query in the status endpoint.
Once the task is created, poll the Get Video Result endpoint (GET /v1/videos/status/{task_id}) until status is completed, then read the generated video URL from the response.

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-2.5-video-edit.

Available options:
seedance-2.5-video-edit
video_urls
string<uri>[]
required

The video to edit (output length follows the input)

Maximum array length: 1
prompt
string
required

Text description of the video to generate

quality
enum<string>
default:720p

Output resolution tier

Available options:
480p,
720p

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