Skip to main content
POST
/
v3
/
async
/
wan2.7-t2v
Wanxiang Wan 2.7 Text-to-Video
curl --request POST \
  --url https://api.highwayapi.ai/v3/async/wan2.7-t2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "size": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "audio_url": "<string>",
  "watermark": true,
  "prompt_extend": true,
  "negative_prompt": "<string>"
}
'
{
  "task_id": "<string>"
}
Wanxiang Wan 2.7 text-to-video model generates smooth videos from text prompts. It supports audio-driven generation or automatic dubbing, supports 720P and 1080P resolutions, durations from 2 to 15 seconds, and is billed by the second. Output includes audio by default.
This is an asynchronous API and returns only the asynchronous task’s task_id. You should use this task_id to request the Get Task Result API to retrieve the generation result.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
seed
integer
Random seed, used to improve the reproducibility of generation results. Value range: [0, 2147483647].Value range: [0, 2147483647]
​
size
string
default:"1920*1080"
Output video resolution (widthheight), which affects cost. 720P tier: 1280720 (16:9), 7201280 (9:16), 960960 (1:1), 1088832 (4:3), 8321088 (3:4). 1080P tier: 19201080 (16:9), 10801920 (9:16), 14401440 (1:1), 16321248 (4:3), 1248*1632 (3:4).Allowed values: 1280*720, 720*1280, 960*960, 1088*832, 832*1088, 1920*1080, 1080*1920, 1440*1440, 1632*1248, 1248*1632
​
prompt
string
required
Text prompt used to describe the elements and visual characteristics expected in the generated video. Chinese and English are supported, up to 1500 characters. Any excess is automatically truncated.Length limit: 0 - 1500
​
duration
integer
default:5
Generated video duration in seconds, billed by the second. An integer in the range [2, 15].Value range: [2, 15]
​
audio_url
string
Audio file URL. The model will use this audio to drive video generation (such as lip-syncing, motion beat matching, etc.). If not provided, the model automatically generates matching background music or sound effects. Supported formats: wav and mp3. Duration: 3–30 seconds; file size no more than 15 MB. If the audio exceeds the video duration, it will be clipped; if it is shorter, the remaining part will be silent.
​
watermark
boolean
default:false
Whether to add a watermark identifier. The watermark is located in the lower-right corner of the video.
​
prompt_extend
boolean
default:true
Whether to enable intelligent prompt rewriting. When enabled, a large model is used to intelligently rewrite the input prompt. This significantly improves generation quality for shorter prompts, but increases processing time.
​
negative_prompt
string
Negative prompt, used to describe content that you do not want to appear in the video frames. Chinese and English are supported, up to 500 characters.Length limit: 0 - 500

​
Response

​
task_id
string
Use task_id to request the Get Task Result API to retrieve the generated output.