Skip to main content
POST
cURL
At least one reference video (the source video to edit) is required.

Editing Constraints

Seedance 2.5 Video Edit is the video-editing sub-task of the omni-reference family on the official discount route. Sending the source video plus explicit edit instructions pins omni_reference_task_type=edit upstream, so the provider validates the constraints at submission time and rejects incompatible parameters immediately with a 400, instead of failing asynchronously minutes later.
  • Source video: at least one reference video is required; the source video must be 4-30 seconds long (validated by the provider per video).
  • Duration: not settable. The model keeps the output length consistent with the source video. The field is not part of the contract - any passed value is silently ignored and -1 is always sent upstream.
  • Aspect ratio: not settable. The output keeps the source video aspect ratio; the field is not part of the contract and any passed value is silently ignored (adaptive is always sent).
  • Reference materials: up to 30 images, 10 videos, and 10 audios; audio cannot be provided on its own.
  • Prompt wording: use explicit edit verbs such as replace, remove, restyle, or change into, and address materials explicitly with @视频N / @图N tokens (for example, 删除 @视频1中的所有人,除了主角。). Ambiguous edit-or-extend prompts may still be re-judged by the model.
Note: When video input is enabled, the unit price is lower because the billing formula differs: without video = unit price × output duration; with video = unit price × (input duration + output duration). Since the output duration follows the source video, the estimated output duration is probed from the source video at billing time.
Want to prolong a video instead? Use Seedance 2.5 Video Extend.

Authorizations

Authorization
string
header
required

Use your APIPod API key as a Bearer token in the Authorization header.

Body

application/json
model
string
required

Public APIPod model ID.

Allowed value: "seedance-2.5-edit"
prompt
string
required

Editing instructions, up to 30000 characters. Use explicit edit verbs such as replace, remove, restyle, or change into, and address materials explicitly with @视频N / @图N tokens (for example, 删除 @视频1中的所有人). It is recommended to keep the prompt to no more than 500 Chinese characters or 1,000 English words.

Maximum string length: 30000
video_urls
string[]
required

Reference video URLs. At least one is required (the source video to edit, 4-30 seconds); up to 10 videos are supported.

Required array length: 1 - 10 elements
image_urls
string[]

Optional reference image URLs (for example the character or style to keep). Up to 30 images are supported; each image must be smaller than 30 MB.

Maximum array length: 30
audio_urls
string[]

Optional reference audio URLs. Up to 10 audios are supported; each audio lasts 2-30 seconds. Audio cannot be provided on its own.

Maximum array length: 10
resolution
enum<string>
default:720p

Generate video resolution.

Available options:
480p,
720p,
1080p
generate_audio
boolean
default:true

Controls whether the generated video contains audio synchronized with the visuals.

Response

200 - application/json

Task accepted

Standard response for task submission

code
integer
required
data
Task Submit Data · object
required

Data content for task submission

message
string
required