ComfyUI Node
Audio To Mouth Track
Derive a synchronized mouth-openness track from an audio waveform.
Audio To Mouth Track
- MOUTH_TRACK
- TIMING
◄audio[]►
◄face_imageneutral►
◄fps24►
◄sample_rate▾►
CategoryParametric/Audio
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | STRING | [] | The input audio. Default []. |
| face_image | STRING | neutral | Face image. Default neutral. |
| fps | INT | 241–240 | Frames per second. From 1 to 240. Default 24. |
| sample_rateopt | COMBO | Sample rate. One of 5 choices. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| MOUTH_TRACK | STRING | — |
| TIMING | FLOAT | — |