You're looking at a specific version of this model. Jump to the model overview.
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| face |
string
|
Input face video or single image
|
|
| audio |
string
|
Input audio or video (audio will be extracted)
|
|
| model_variant |
None
|
wav2lip
|
Choose base or GAN model
|
| static |
boolean
|
False
|
Use first video frame only (auto-detected for images, ignored for videos)
|
| fps |
number
|
25
|
FPS if using static image
|
| pads |
array
|
[0, 10, 0, 0]
|
Padding: top bottom left right
|
| wav2lip_batch_size |
integer
|
128
|
Batch size
|
| resize_factor |
integer
|
1
|
Downscale factor for frames before processing
|
| out_height |
integer
|
480
|
Output video height (e.g., 480 or 720)
|
| crop |
array
|
[0, -1, 0, -1]
|
Crop region: top bottom left right (-1 auto)
|
| box |
array
|
[-1, -1, -1, -1]
|
Constant face bbox: top bottom left right (-1 disabled)
|
| rotate |
boolean
|
False
|
Rotate input video 90 degrees clockwise
|
| nosmooth |
boolean
|
False
|
Disable bbox smoothing
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}