Wan — Create a digital human video

Create a talking, singing, or performing video from a portrait image and an audio file

POST

/services/aigc/image2video/video-synthesis

cURL

# China North 2 (Beijing). This model is available only in this region.
# API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
curl --request POST \
  --url https://cn-beijing.maas.qwencloudapi.com/api/v1/services/aigc/image2video/video-synthesis \
  --header 'X-DashScope-Async: enable' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan2.2-s2v",
    "input": {
      "image_url": "https://img.alicdn.com/imgextra/i3/O1CN011FObkp1T7Ttowoq4F_!!6000000002335-0-tps-1440-1797.jpg",
      "audio_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250825/iaqpio/input_audio.MP3"
    },
    "parameters": {
      "resolution": "480P"
    }
  }'

{
  "output": {
    "task_id": "a8532587-fa8c-4ef8-82be-xxxxxx",
    "task_status": "PENDING"
  },
  "request_id": "7574ee8f-38a3-4b1e-9280-xxxxxx"
}

wan2.2-s2v creates a natural-looking talking, singing, or performing video from a single portrait image and an audio file. The generated video matches the duration of the input audio. Supported regions: China North 2 (Beijing) only. Use an API key created in that region and the https://cn-beijing.maas.qwencloudapi.com endpoint. See Regions and endpoints.

Image: JPG, JPEG, PNG, BMP, or WEBP; width and height between 400 and 7,000 pixels; publicly accessible HTTP or HTTPS URL.
Audio: WAV or MP3; under 15 MB and under 20 seconds; clear human speech without background noise or music.
Video length: The output video lasts as long as the input audio. To generate a longer video, split the audio into segments shorter than 20 seconds, generate one video per segment, and merge the results.

Authorizations

string

header

required

QwenCloud API key. See Get an API key.

Header Parameters

enum<string>

required

Fixed value: enable. Indicates an asynchronous call.

Available options:enable

Body

application/json

enum<string>

required

The model to call.

Available options:wan2.2-s2v

Example:wan2.2-s2v

object

required

Show child attributes

string

required

URL of the input image.

Formats: jpg, jpeg, png, bmp, webp.
Resolution: both width and height must be between 400 and 7000 pixels.
Only publicly accessible HTTP or HTTPS URLs are supported. To upload a local file and get a temporary URL, see Upload a file and get a temporary URL.

Example:https://example.com/portrait.jpg

string

required

URL of the input audio file.

Formats: wav, mp3.
Limits: file size less than 15 MB, duration less than 20 seconds.
Content: must contain clear, loud human speech with no background noise or music.
Only publicly accessible HTTP or HTTPS URLs are supported. To upload a local file and get a temporary URL, see Upload a file and get a temporary URL.

Example:https://example.com/speech.mp3

object

Show child attributes

enum<string>

default"480P"

Output resolution. Valid values: 480P and 720P. Default: 480P.

The model keeps the aspect ratio of the input image and scales the total pixel count close to the selected tier.

480P: typically 640x480 (about 310,000 pixels), aspect ratio 4:3.
720P: typically 1280x720 (about 920,000 pixels), aspect ratio 16:9.

Available options:480P,720P

Example:480P

Response

200-application/json

object

Show child attributes

string

Unique ID of the asynchronous task.

Example:a8532587-fa8c-4ef8-82be-0c46b17950d1

string

Task status after submission.

Example:PENDING

string

Unique ID of this request.

Example:7574ee8f-38a3-4b1e-9280-11c33ab46e51