ComfyUI Node
Smart Audio Chunker
Smart Audio Chunker is used to take an audio segment and split it up in chunks. It searches for silence to split up the audio. It also adds some silence to the chunks specifically for LTX
Smart Audio Chunker
- audio
- num_chunks
- chunk_size
- start_time
- total_duration
◄index0►
◄chunk_secs10►
◄variation2►
CategoryHandyNodes-KT
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | the Full audio that will get chunked | |
| index | INT | 0 | Index from the for loop |
| chunk_secs | INT | 10 | Size of an Audio Chunk, for low VRAM use 5 |
| variation | INT | 2 | we separate when we find silence, this tells how far back and forward to search for silence |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| num_chunks | INT | Number Chunks Calculated for the audio. |
| chunk_size | FLOAT | length of chunk in seconds |
| start_time | FLOAT | start time of chunk in audio |
| total_duration | FLOAT | end time in chunk in audio |