Skip to main content
POST
/
wan
/
api
/
v1
/
services
/
aigc
/
video-generation
/
video-synthesis
Text-to-video: create a video generation task from a text prompt
curl --request POST \
  --url https://api.apiyi.com/wan/api/v1/services/aigc/video-generation/video-synthesis \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'X-DashScope-Async: <x-dashscope-async>' \
  --data '
{
  "model": "wan2.7-t2v",
  "input": {
    "prompt": "A lighthouse on the seashore at dusk, the camera slowly pushing in, waves gently lapping the rocks, seabirds calling, cinematic lighting, steady camera work"
  }
}
'
{
  "output": {
    "task_id": "c2e7570c-0af2-4eba-919f-3af3d1164a38",
    "task_status": "PENDING"
  },
  "request_id": "a23b81b0-0c05-9972-a6c9-ee757400afdb"
}

Documentation Index

Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt

Use this file to discover all available pages before exploring further.

The Playground on the right lets you debug directly: put Bearer sk-your-api-key in Authorization, fill in model / input / parameters, and send the request. A successful submission returns a task_id; see below for polling and download.
This page is the creation endpoint for wan2.7-t2v (text-to-video). It needs only a text prompt, no media. To make an image move or preserve subject features, use Image-to-Video / Reference-to-Video instead. For the full async flow, status table, and Python client, see the Wan Overview.
  • Creation requests must go to /wan/api/v1/services/aigc/video-generation/video-synthesis with the header X-DashScope-Async: enable. Do not use /v1/videos.
  • duration must be an integer (5, not "5"); write resolution in uppercase (720P).

Code examples

curl -X POST "https://api.apiyi.com/wan/api/v1/services/aigc/video-generation/video-synthesis" \
  -H "X-DashScope-Async: enable" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-t2v",
    "input": {
      "prompt": "A lighthouse on the seashore at dusk, the camera slowly pushing in, waves gently lapping the rocks, seabirds calling, cinematic lighting, steady camera work"
    },
    "parameters": {
      "resolution": "720P",
      "duration": 5,
      "prompt_extend": true,
      "watermark": true
    }
  }'

Parameter quick reference

ParameterTypeRequiredDefaultNotes
modelstringFixed wan2.7-t2v
input.promptstringText prompt; describe scene, camera motion, lighting, and style
input.negative_promptstringNegative prompt, ≤500 characters
parameters.resolutionstring720P720P / 1080P (uppercase)
parameters.ratiostring16:916:9 / 9:16 / 1:1 / 4:3 / 3:4
parameters.durationint52-15 second integer
parameters.prompt_extendbooltrueSmart rewriting, recommended on
parameters.watermarkboolfalse”AI generated” watermark in the bottom-right corner
parameters.seedintrandom0-2147483647, fix for reproducibility

Response format

A successful creation returns a task_id (not the video itself):
{
  "output": { "task_id": "c2e7570c-0af2-4eba-919f-3af3d1164a38", "task_status": "PENDING" },
  "request_id": "a23b81b0-0c05-9972-a6c9-ee757400afdb"
}
After submitting, poll GET /v1/tasks/{task_id} until status: "completed", then download the mp4 from the response’s result_url. Do not send the Authorization header when downloading (OSS signed direct link); result_url expires in 24 hours by default. For the full polling loop and Python client, see Wan Overview · Async call flow.

Authorizations

Authorization
string
header
required

The API Key obtained from the APIYI console

Headers

X-DashScope-Async
enum<string>
default:enable
required

Async processing switch; must be set to enable, otherwise it returns current user api does not support synchronous calls

Available options:
enable

Body

application/json
model
enum<string>
default:wan2.7-t2v
required

Model ID; for text-to-video, fixed wan2.7-t2v (legacy version wan2.6-t2v)

Available options:
wan2.7-t2v,
wan2.6-t2v
input
object
required
parameters
object

Response

Task submitted; returns task_id and PENDING status

output
object
request_id
string

Unique request identifier; provide it to support when troubleshooting

Example:

"a23b81b0-0c05-9972-a6c9-ee757400afdb"