> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apipod.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Seedance 2.5 Video Edit
> Seedance 2.5 Video Edit pins the omni-reference task type to video editing: provide the source video, describe the edit, and the output duration and aspect ratio automatically follow the source video.
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](/seedance/2-5-video-extend).
## OpenAPI
````yaml api-reference/openapi/seedance--2-5-video-edit.yaml POST /v1/videos/generations
openapi: 3.1.0
info:
title: Seedance 2.5 Video Edit API
version: 1.0.0
description: >-
Seedance 2.5 Video Edit pins the upstream omni-reference task type to video
editing. Provide the source video (4-30 seconds) plus optional reference
images or audios and describe the edit; the output keeps the source
timeline, aspect ratio, and duration - duration and aspect_ratio are not
settable (the fields are not exposed and any passed values are ignored). The
required source video is validated at submission time, so missing materials
fail fast instead of erroring asynchronously. In APIPod, the public model ID
is seedance-2.5-edit, and results are returned through asynchronous video
tasks.
servers:
- url: https://api.apipod.ai
description: Production
security: []
paths:
/v1/videos/generations:
post:
tags:
- Seedance 2.5 Video Edit
summary: Create Generation Task
description: >-
Seedance 2.5 Video Edit pins the upstream omni-reference task type to
video editing. Provide the source video (4-30 seconds) plus optional
reference images or audios and describe the edit; the output keeps the
source timeline, aspect ratio, and duration - duration and aspect_ratio
are not settable (the fields are not exposed and any passed values are
ignored). The required source video is validated at submission time, so
missing materials fail fast instead of erroring asynchronously. In
APIPod, the public model ID is seedance-2.5-edit, and results are
returned through asynchronous video tasks.
operationId: create-seedance-2-5-video-edit
requestBody:
required: true
content:
application/json:
schema:
type: object
title: Seedance 2.5 Video Edit
properties:
model:
type: string
title: Model ID
description: Public APIPod model ID.
const: seedance-2.5-edit
prompt:
type: string
title: Prompt
description: >-
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.
maxLength: 30000
image_urls:
type: array
title: Image Urls
description: >-
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.
maxItems: 30
items:
type: string
video_urls:
type: array
title: Video Urls
description: >-
Reference video URLs. At least one is required (the source
video to edit, 4-30 seconds); up to 10 videos are supported.
minItems: 1
maxItems: 10
items:
type: string
audio_urls:
type: array
title: Audio Urls
description: >-
Optional reference audio URLs. Up to 10 audios are
supported; each audio lasts 2-30 seconds. Audio cannot be
provided on its own.
maxItems: 10
items:
type: string
resolution:
type: string
title: Resolution
description: Generate video resolution.
enum:
- 480p
- 720p
- 1080p
default: 720p
generate_audio:
type: boolean
title: Generate Audio
description: >-
Controls whether the generated video contains audio
synchronized with the visuals.
default: true
required:
- model
- prompt
- video_urls
example:
model: seedance-2.5-edit
prompt: 视频编辑：删除 @视频1中的所有人，除了主角。
video_urls:
- >-
https://arkdocs.tos-cn-beijing.volces.com/videos/video-generation/seedance2.5_edit_input.mov
resolution: 480p
web_search: false
generate_audio: true
responses:
'200':
description: Task accepted
content:
application/json:
schema:
type: object
title: Task Submit Response
description: Standard response for task submission
properties:
code:
type: integer
data:
type: object
title: Task Submit Data
description: Data content for task submission
properties:
task_id:
type: string
description: generatation task id
message:
type: string
required:
- code
- message
- data
example:
code: 200
message: success
data:
task_id: vid_task_01JEXAMPLE
security:
- bearerAuth: []
x-codeSamples:
- lang: Shell
label: cURL
source: |-
curl https://api.apipod.ai/v1/videos/generations \
-H "Authorization: Bearer $APIPOD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.5-edit",
"prompt": "视频编辑：删除 @视频1中的所有人，除了主角。",
"video_urls": ["https://arkdocs.tos-cn-beijing.volces.com/videos/video-generation/seedance2.5_edit_input.mov"],
"resolution": "480p",
"web_search": false,
"generate_audio": true
}'
- lang: Python
label: Python
source: |-
import os
import requests
payload = {
"model": "seedance-2.5-edit",
"prompt": "视频编辑：删除 @视频1中的所有人，除了主角。",
"video_urls": ["https://arkdocs.tos-cn-beijing.volces.com/videos/video-generation/seedance2.5_edit_input.mov"],
"resolution": "480p",
"web_search": False,
"generate_audio": True
}
response = requests.post(
"https://api.apipod.ai/v1/videos/generations",
headers={
"Authorization": f"Bearer {os.environ['APIPOD_API_KEY']}",
"Content-Type": "application/json",
},
json=payload,
timeout=60,
)
response.raise_for_status()
print(response.json())
- lang: Go
label: Go
source: |-
package main
import (
"bytes"
"encoding/json"
"fmt"
"net/http"
"os"
)
func main() {
payload := map[string]any{}
if err := json.Unmarshal([]byte(`{
"model": "seedance-2.5-edit",
"prompt": "视频编辑：删除 @视频1中的所有人，除了主角。",
"video_urls": ["https://arkdocs.tos-cn-beijing.volces.com/videos/video-generation/seedance2.5_edit_input.mov"],
"resolution": "480p",
"web_search": false,
"generate_audio": true
}`), &payload); err != nil {
panic(err)
}
body, err := json.Marshal(payload)
if err != nil {
panic(err)
}
req, err := http.NewRequest(http.MethodPost, "https://api.apipod.ai/v1/videos/generations", bytes.NewReader(body))
if err != nil {
panic(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("APIPOD_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
fmt.Println(resp.Status)
}
- lang: Rust
label: Rust
source: |-
use reqwest::Client;
use serde_json::json;
use std::env;
#[tokio::main]
async fn main() -> Result<(), Box> {
let payload = json!({
"model": "seedance-2.5-edit",
"prompt": "视频编辑：删除 @视频1中的所有人，除了主角。",
"video_urls": ["https://arkdocs.tos-cn-beijing.volces.com/videos/video-generation/seedance2.5_edit_input.mov"],
"resolution": "480p",
"web_search": false,
"generate_audio": true
});
let response = Client::new()
.post("https://api.apipod.ai/v1/videos/generations")
.bearer_auth(env::var("APIPOD_API_KEY")?)
.json(&payload)
.send()
.await?
.error_for_status()?;
println!("{}", response.text().await?);
Ok(())
}
- lang: JavaScript
label: JavaScript
source: >-
const response = await
fetch("https://api.apipod.ai/v1/videos/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.APIPOD_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify(
{
"model": "seedance-2.5-edit",
"prompt": "视频编辑：删除 @视频1中的所有人，除了主角。",
"video_urls": ["https://arkdocs.tos-cn-beijing.volces.com/videos/video-generation/seedance2.5_edit_input.mov"],
"resolution": "480p",
"web_search": false,
"generate_audio": true
}
),
});
if (!response.ok) {
throw new Error(`APIPod request failed: ${response.status} ${await response.text()}`);
}
console.log(await response.json());
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: APIPod API key
description: Use your APIPod API key as a Bearer token in the Authorization header.
````