
sync/lipsync-2-pro
Public
37
runs
Run sync/lipsync-2-pro with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
---|---|---|---|
video |
string
|
Input video file (.mp4)
|
|
audio |
string
|
Input audio file (.wav)
|
|
sync_mode |
None
|
loop
|
Lipsync mode when audio and video durations are out of sync
|
temperature |
number
|
0.5
Max: 1 |
How expressive lipsync can be (0-1)
|
active_speaker |
boolean
|
False
|
Whether to detect active speaker (i.e. whoever is speaking in the clip will be used for lipsync)
|
{
"type": "object",
"title": "Input",
"required": [
"video",
"audio"
],
"properties": {
"audio": {
"type": "string",
"title": "Audio",
"x-order": 1,
"description": "Input audio file (.wav)"
},
"video": {
"type": "string",
"title": "Video",
"x-order": 0,
"description": "Input video file (.mp4)"
},
"sync_mode": {
"enum": [
"loop",
"bounce",
"cut_off",
"silence",
"remap"
],
"type": "string",
"title": "sync_mode",
"description": "Lipsync mode when audio and video durations are out of sync",
"default": "loop",
"x-order": 2
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 0.5,
"maximum": 1,
"minimum": 0,
"x-order": 3,
"description": "How expressive lipsync can be (0-1)"
},
"active_speaker": {
"type": "boolean",
"title": "Active Speaker",
"default": false,
"x-order": 4,
"description": "Whether to detect active speaker (i.e. whoever is speaking in the clip will be used for lipsync)"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}