Wan 2.6 Video Reference

POST /v3/async/wan2.6-v2v

Wan 2.6 Video Reference

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/async/wan2.6-v2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "input": {
    "prompt": "<string>",
    "audio_url": "<string>",
    "reference_urls": [
      {}
    ],
    "negative_prompt": "<string>"
  },
  "parameters": {
    "seed": 123,
    "size": "<string>",
    "audio": true,
    "duration": 123,
    "shot_type": "<string>",
    "watermark": true,
    "prompt_extend": true
  }
}
'

200

{
  "task_id": "<string>"
}

This is an async API that only returns the async task_id. Use the task_id to call the Get Async Task Result API to retrieve the video generation result.

This is an async API that only returns the task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.

Request Headers

Content-Type · string · required

Enum: application/json

Authorization · string · required

Bearer authentication format: Bearer {{API Key}}.

Request Body

input · object · required

Hide properties

prompt · string · required

Text prompt describing the desired elements and visual characteristics in the generated video. Supports Chinese and English; each Chinese character or letter counts as one character. Content exceeding the limit will be automatically truncated.

Length limit: 0 - 2000

audio_url · string

Audio file URL; the model will use this audio to generate the video. Supports HTTP or HTTPS protocols. Audio requirements: formats wav, mp3; duration 3-30 seconds; file size max 15MB. Overflow handling: if the audio length exceeds the duration value (5 or 10 seconds), only the first 5 or 10 seconds are used and the rest is discarded. If the audio is shorter than the video duration, the portion beyond the audio length will be silent. For example, if the audio is 3 seconds and the video duration is 5 seconds, the output video will have audio for the first 3 seconds and silence for the last 2 seconds.

reference_urls · array · required

Reference video URLs, ordered sequentially. Reference videos are referred to as characterx in the prompt. For example, with two reference videos, write the prompt as “character1 sings by the roadside, character2 dances nearby”. Even with a single reference, you must write character1 with the number 1.

Array length: 1 - 3

Formats: mp4, mov. Quantity: 1-3 videos. Duration: 2-30 seconds per video. Max file size: 30MB per video. Cannot be used simultaneously with audio.

negative_prompt · string

Negative prompt describing content you do not want to appear in the video. Supports Chinese and English, up to 500 characters; content exceeding the limit will be automatically truncated.

Length limit: 0 - 500

parameters · object

Hide properties

seed · integer

Random seed. Range: [0, 2147483647]. When not specified, a random seed is automatically generated. To improve reproducibility, set a fixed seed value. Note that due to the probabilistic nature of model generation, even with the same seed, results may not be completely identical.

Range: [0, 2147483647]

size · string · default: "1920*1080"

Specifies the output video resolution in widthheight format. Supports 720P tier (1280720/7201280/960960/1088832/8321088) and 1080P tier (19201080/10801920/14401440/16321248/1248*1632).

Possible values: 1280*720, 720*1280, 960*960, 1088*832, 832*1088, 1920*1080, 1080*1920, 1440*1440, 1632*1248, 1248*1632

audio · boolean · default: true

Whether to add audio. Parameter priority: audio_url > audio; only takes effect when audio_url is empty. true: default, automatically adds audio to the video; false: no audio, outputs a silent video.

duration · integer · default: 5

Duration of the generated video in seconds. Available values: 5, 10. Default: 5. Duration directly affects cost (cost = unit price based on resolution x duration in seconds); please confirm model pricing before calling.

Possible values: 5, 10

shot_type · string · default: "multi"

Video generation mode. single: single-shot generation; multi: multi-shot generation.

Possible values: single, multi

watermark · boolean · default: false

Whether to add a watermark. The watermark is placed in the bottom-right corner with fixed text “AI Generated”. false: default, no watermark; true: add watermark.

prompt_extend · boolean · default: true

Whether to enable intelligent prompt rewriting. When enabled, a language model rewrites the input prompt. This significantly improves results for shorter prompts but increases processing time. true: default, enable intelligent rewriting; false: disable intelligent rewriting.

Response

task_id · string · required

Use the task_id to call the Get Async Task Result API to retrieve the generated output.