Wan 2.7 Text-to-Video
Video Generator
Wan 2.7 Text-to-Video
POST
Wan 2.7 Text-to-Video
Wan 2.7 Text-to-Video model generates smooth videos from text prompts. Supports audio-driven generation or automatic soundtrack. 720P and 1080P resolutions, duration 2~15 seconds, billed per second. Output includes audio by default.
Request Headers
string
erforderlich
Supports:
application/jsonstring
erforderlich
Bearer authentication format, for example: Bearer {{API Key}}.
Request Body
integer
Random seed for improving reproducibility. Range: [0, 2147483647].Value range: [0, 2147483647]
string
Standard:"1920*1080"
Output video resolution (widthheight), affects pricing. 720P: 1280720 (16:9), 7201280 (9:16), 960960 (1:1), 1088832 (4:3), 8321088 (3:4). 1080P: 19201080 (16:9), 10801920 (9:16), 14401440 (1:1), 16321248 (4:3), 1248*1632 (3:4).Optional values:
1280*720, 720*1280, 960*960, 1088*832, 832*1088, 1920*1080, 1080*1920, 1440*1440, 1632*1248, 1248*1632string
erforderlich
Text prompt describing desired video content. Supports Chinese and English, max 1500 characters. Exceeding portion is automatically truncated.Length limit: 0 - 1500
integer
Standard:5
Video duration in seconds, billed per second. Range: [2, 15] integer.Value range: [2, 15]
string
Audio file URL. Model will use this audio to drive video generation (lip-sync, beat-matching, etc.). If not provided, model auto-generates matching background music or sound effects. Formats: wav, mp3. Duration: 3~30s. Max size: 15MB. If audio exceeds video duration it is truncated; if shorter, remaining video is silent.
boolean
Standard:false
Add watermark to the output video (bottom-right corner).
boolean
Standard:true
Enable intelligent prompt rewriting. Uses a language model to enhance short prompts, improving generation quality at the cost of slightly longer processing time.
string
Negative prompt describing undesired content in the video. Supports Chinese and English, max 500 characters.Length limit: 0 - 500
Response
string
Use the task_id to request the Task Result API to retrieve the generated outputs.
Zuletzt geändert am 15. Mai 2026