ComfyUI Node
Extract nTh Audio track
This node extracts all the track info enterd by the user and then sorts them and combines them so it can subsequentally loop thru them in the workflow
Extract nTh Audio track
- fullaudio
- audioTrack
- totalTracks
- numFrames
- speakerNum
- front_pad_ms
- end_pad_ms
◄combinedTrackInfo1—►
◄combinedTrackInfo2—►
◄padAudioForLtxtrue►
◄index1►
◄addBreathNoisefalse►
CategoryTKNodes
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| fullaudio | AUDIO | — | |
| combinedTrackInfo1 | STRING | Speaker 1 track info. | |
| combinedTrackInfo2 | STRING | Speaker 2 track info. | |
| padAudioForLtx | BOOLEAN | true | pad audio track with silence..helps lip sync. |
| index | INT | 11–10 | the track number from ALL tracks |
| addBreathNoiseopt | BOOLEAN | false | This will add human breath to start of audio, turn this ON increases chances of lip sync working. |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| audioTrack | AUDIO | — |
| totalTracks | INT | — |
| numFrames | INT | — |
| speakerNum | INT | — |
| front_pad_ms | INT | — |
| end_pad_ms | INT | — |