irulkenzei/musetalk
Run irulkenzei/musetalk 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 |
|---|---|---|---|
| face |
string
|
Source face -- a still image or a talking-head video. This identity gets lip-synced to 'audio'.
|
|
| audio |
string
|
Driving audio (wav/mp3/etc.) that the face's mouth will be synced to.
|
|
| version |
None
|
v15
|
MuseTalk model version. v15 is the recommended/higher-quality version.
|
| bbox_shift |
integer
|
0
Min: -9 Max: 9 |
Vertical face bounding-box shift in pixels (v1 only, ignored for v15). Positive = lower mouth region.
|
| extra_margin |
integer
|
10
Max: 40 |
Extra chin margin in pixels for the face crop (v15 only).
|
| parsing_mode |
None
|
jaw
|
Face mask blending mode used when compositing the generated mouth back onto the source frame (v15 only).
|
| left_cheek_width |
integer
|
90
Min: 20 Max: 160 |
Left cheek mask width in pixels (v15 only).
|
| right_cheek_width |
integer
|
90
Min: 20 Max: 160 |
Right cheek mask width in pixels (v15 only).
|
| fps |
integer
|
25
Min: 1 Max: 60 |
Output frame rate. Only used when 'face' is a still image -- a video 'face' input keeps its own source FPS.
|
| audio_padding_length_left |
integer
|
2
Max: 10 |
Left audio context padding, in Whisper feature frames.
|
| audio_padding_length_right |
integer
|
2
Max: 10 |
Right audio context padding, in Whisper feature frames.
|
| batch_size |
integer
|
8
Min: 1 Max: 32 |
Inference batch size. Lower this if you hit GPU out-of-memory.
|
| use_float16 |
boolean
|
True
|
Run in float16 for lower VRAM usage and faster inference, at a small quality cost.
|
{
"type": "object",
"title": "Input",
"required": [
"face",
"audio"
],
"properties": {
"fps": {
"type": "integer",
"title": "Fps",
"default": 25,
"maximum": 60,
"minimum": 1,
"x-order": 8,
"description": "Output frame rate. Only used when 'face' is a still image -- a video 'face' input keeps its own source FPS."
},
"face": {
"type": "string",
"title": "Face",
"format": "uri",
"x-order": 0,
"description": "Source face -- a still image or a talking-head video. This identity gets lip-synced to 'audio'."
},
"audio": {
"type": "string",
"title": "Audio",
"format": "uri",
"x-order": 1,
"description": "Driving audio (wav/mp3/etc.) that the face's mouth will be synced to."
},
"version": {
"enum": [
"v15",
"v1"
],
"type": "string",
"title": "version",
"description": "MuseTalk model version. v15 is the recommended/higher-quality version.",
"default": "v15",
"x-order": 2
},
"batch_size": {
"type": "integer",
"title": "Batch Size",
"default": 8,
"maximum": 32,
"minimum": 1,
"x-order": 11,
"description": "Inference batch size. Lower this if you hit GPU out-of-memory."
},
"bbox_shift": {
"type": "integer",
"title": "Bbox Shift",
"default": 0,
"maximum": 9,
"minimum": -9,
"x-order": 3,
"description": "Vertical face bounding-box shift in pixels (v1 only, ignored for v15). Positive = lower mouth region."
},
"use_float16": {
"type": "boolean",
"title": "Use Float16",
"default": true,
"x-order": 12,
"description": "Run in float16 for lower VRAM usage and faster inference, at a small quality cost."
},
"extra_margin": {
"type": "integer",
"title": "Extra Margin",
"default": 10,
"maximum": 40,
"minimum": 0,
"x-order": 4,
"description": "Extra chin margin in pixels for the face crop (v15 only)."
},
"parsing_mode": {
"enum": [
"jaw",
"raw",
"neck"
],
"type": "string",
"title": "parsing_mode",
"description": "Face mask blending mode used when compositing the generated mouth back onto the source frame (v15 only).",
"default": "jaw",
"x-order": 5
},
"left_cheek_width": {
"type": "integer",
"title": "Left Cheek Width",
"default": 90,
"maximum": 160,
"minimum": 20,
"x-order": 6,
"description": "Left cheek mask width in pixels (v15 only)."
},
"right_cheek_width": {
"type": "integer",
"title": "Right Cheek Width",
"default": 90,
"maximum": 160,
"minimum": 20,
"x-order": 7,
"description": "Right cheek mask width in pixels (v15 only)."
},
"audio_padding_length_left": {
"type": "integer",
"title": "Audio Padding Length Left",
"default": 2,
"maximum": 10,
"minimum": 0,
"x-order": 9,
"description": "Left audio context padding, in Whisper feature frames."
},
"audio_padding_length_right": {
"type": "integer",
"title": "Audio Padding Length Right",
"default": 2,
"maximum": 10,
"minimum": 0,
"x-order": 10,
"description": "Right audio context padding, in Whisper feature frames."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}