Wan2.7 Text to Video
- Wan 2.7 text-to-video model, supporting text-to-video generation, audio-driven generation, optional prompt expansion, and safety checking
- Async processing mode, use the returned task ID to query task status
- Generated video links are valid for 24 hours, please save them promptly
Authorizations
All APIs require Bearer Token authentication
Add to request header:
Authorization: Bearer YOUR_API_KEY
Body
wan-2.7-text-to-video: Text to Video
"wan-2.7-text-to-video"
Prompt describing the expected video content to generate
5000"A lone surfer crossing bioluminescent waves at night"
Output video aspect ratio
Options: 16:9, 9:16, 1:1, 4:3, 3:4
16:9, 9:16, 1:1, 4:3, 3:4 "16:9"
Output video duration in seconds, supports integer values from 2-15
2 <= x <= 152
Output video resolution
Options: 720p, 1080p
720p, 1080p "720p"
Public URL of the driving audio
**Notes: **
- Supports WAV / MP3
- Model generates background music automatically if not provided
"https://example.com/music.mp3"
Negative prompt describing content to avoid
500"blurry, jitter"
Random seed for reproducibility
0 <= x <= 2147483647123
Whether to enable prompt expansion. Uses model default if not specified
true
Whether to enable safety checker. Uses model default if not specified
true
Response
Task created successfully
Task creation timestamp
1757165031
Task ID
"task-unified-1757165031-uyujaw3d"
Actual model name used
Specific task type
video.generation.task Task progress percentage (0-100)
0 <= x <= 1000
Task status
pending, processing, completed, failed "pending"
Asynchronous task information
Task output type
video "video"