Wan 2.5 Preview - Text to Video

wan25_t2v_preview

Wan 2.5 Preview - Text to Video generates video from text prompts.

Endpoints

POST /v1/queue/wan25_t2v_preview # Create task

GET /v1/queue/wan25_t2v_preview/requests/{request_id}/status # Check status

GET /v1/queue/wan25_t2v_preview/requests/{request_id}/response # Get result

PUT /v1/queue/wan25_t2v_preview/requests/{request_id}/cancel # Cancel task

Request parameters

curl --location "https://cloud.seaart.ai/model/v1/queue/wan25_t2v_preview" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "Wan25 audit t2v with official audio URL: a small red cube moves across a clean white studio table.",
    "negative_prompt": "low quality, blurry",
    "audio_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250923/hbiayh/%E4%BB%8E%E5%86%9B%E8%A1%8C.mp3",
    "size": "832*480",
    "duration": 5,
    "prompt_extend": false,
    "seed": 12345,
    "watermark": false
  }'

prompt string required

Text prompt describing the expected elements and visual characteristics in the generated video.

Chinese and English are supported. Content beyond the model limit is automatically truncated.

duration int

Video duration in seconds. This parameter affects generation cost.

Options: 5, 10

Example: 5

negative_prompt string

Negative prompt describing content that should not appear in the video. It can be used to constrain the video. Chinese and English are supported. Maximum length: 500 characters. Extra content is automatically truncated.

audio_url string

Audio file URL. The model uses this audio to generate the video.

Audio formats: wav, mp3

Audio duration: 3 - 30s

File size: no more than 15MB

Over-limit handling: if the audio length exceeds the duration value, such as 5 seconds, the first 5 seconds are kept and the rest is discarded. If the audio is shorter than the video duration, the part beyond the audio length is silent. For example, if the audio is 3 seconds and the video duration is 5 seconds, the first 3 seconds have sound and the last 2 seconds are silent.

size string

Generated video resolution in width*height format. size must be a concrete value such as 1280*720, not 1:1 or 480P.

480P tier: 832*480 (16:9), 480*832 (9:16), 624*624 (1:1).

720P tier: 1280*720 (16:9), 720*1280 (9:16), 960*960 (1:1), 1088*832 (4:3), 832*1088 (3:4).

1080P tier: 1920*1080 (16:9), 1080*1920 (9:16), 1440*1440 (1:1), 1632*1248 (4:3), 1248*1632 (3:4).

Default: 1920*1080

prompt_extend bool

Whether to enable intelligent prompt rewriting. When enabled, a large model rewrites the input prompt, which can significantly improve short-prompt results but increases latency.

Options: true, false

seed int

Random seed. If omitted, the system automatically generates a random seed. Fixing seed can improve reproducibility, but the same seed does not guarantee identical results every time.

Range: 0 - 2147483647

watermark bool

Whether to add a watermark in the lower-right corner of the video.

Options: false, true

Response parameters

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://cloud.seaart.ai/model/v1/queue/wan25_t2v_preview/requests/mmsu_01hxyz.../response",
  "status_url": "https://cloud.seaart.ai/model/v1/queue/wan25_t2v_preview/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://cloud.seaart.ai/model/v1/queue/wan25_t2v_preview/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Field	Type	Description
`request_id`	string	Task ID used for all follow-up operations.
`response_url`	string	URL to fetch the final result.
`status_url`	string	URL to query task status.
`cancel_url`	string	URL to cancel the task.
`queue_position`	int	Current queue position.

Follow-up operations

Check status

Get result

Cancel task

Error handling