Files
2026-06-07 20:50:19 -07:00

268 lines
6.0 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"id": "18bb6f1f-5453-484d-9a6d-260b40f4e887",
"revision": 0,
"last_node_id": 7,
"last_link_id": 11,
"nodes": [
{
"id": 2,
"type": "LoadAudio",
"pos": [
-1062.0764835957827,
359.223383951974
],
"size": [
282.798828125,
136
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"chatterbox_input_target_voice.mp3",
null,
null
]
},
{
"id": 5,
"type": "AudioCrop",
"pos": [
-738.5534728009812,
170.18822419548158
],
"size": [
270,
82
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 5
}
],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
10
]
}
],
"properties": {
"Node name for S&R": "AudioCrop"
},
"widgets_values": [
"0:00",
"0:27"
]
},
{
"id": 1,
"type": "FL_ChatterboxVC",
"pos": [
-427.25661449685225,
167.3668274611146
],
"size": [
277.015625,
150
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "input_audio",
"type": "AUDIO",
"link": 10
},
{
"name": "target_voice",
"type": "AUDIO",
"link": 11
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
4
]
},
{
"name": "message",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "FL_ChatterboxVC"
},
"widgets_values": [
1956129161,
"randomize",
false,
false
]
},
{
"id": 7,
"type": "MarkdownNote",
"pos": [
-1500,
170
],
"size": [
402.81050958333503,
667.0051882662111
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "šŸŽ™ļø Chatterbox Voice Cloning (Audio → Audio)",
"properties": {},
"widgets_values": [
"This workflow takes one audio clip and converts it into another voice while preserving the original timing and performance.\n\n---\n\n## What This Does\n\n- **Input audio**: the speech or performance you want to convert \n- **Target voice**: a short reference clip of the voice you want to clone \n- **Output**: the original audio re-spoken in the target voice\n\n---\n\n## How to Use\n\n### 1. Load the Source Audio\n- Upload the audio you want to convert into the **top Load Audio** node \n- This is the performance that will be re-voiced\n\n### 2. (Optional) Trim the Audio\n- Use **AudioCrop** to select a specific section \n- Adjust `start_time` and `end_time` to isolate the part you want\n- You can bypass the **AudioCrop** node if you don't need to trim your clip\n\n### 3. Load the Target Voice\n- Upload a short reference clip into the **bottom Load Audio** node \n- 5–10 seconds of clean speech works well \n- This audio defines the cloned voice\n\n### 4. Generate the Voice Conversion\n- The **FL Chatterbox VC** node takes:\n - `input_audio` → the source performance\n - `target_voice` → the voice reference\n- Click **Run** to generate\n\n### 5. Listen or Export\n- Preview the result in **Save Audio (MP3)** \n- The output keeps the original timing, phrasing, and cadence\n\n---\n\n## Tips\n\n- Clean, single-speaker reference clips give the best results \n- Shorter, well-cropped segments are more reliable \n- If results sound off, try trimming silence or reducing background noise\n\n---\n"
],
"color": "#222",
"bgcolor": "#000"
},
{
"id": 4,
"type": "SaveAudioMP3",
"pos": [
-116.61273975353727,
165.40033076921117
],
"size": [
270,
136
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 4
}
],
"outputs": [],
"properties": {
"Node name for S&R": "SaveAudioMP3"
},
"widgets_values": [
"audio/HanzoStudio",
"V0"
]
},
{
"id": 3,
"type": "LoadAudio",
"pos": [
-1063.0168912935958,
168.30728251554427
],
"size": [
282.798828125,
136
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
5
]
}
],
"properties": {
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"chatterbox_input_gettysburg.wav",
null,
null
]
}
],
"links": [
[
4,
1,
0,
4,
0,
"AUDIO"
],
[
5,
3,
0,
5,
0,
"AUDIO"
],
[
10,
5,
0,
1,
0,
"AUDIO"
],
[
11,
2,
0,
1,
1,
"AUDIO"
]
],
"groups": [],
"config": {},
"extra": {
"workflowRendererVersion": "LG",
"ds": {
"scale": 0.5875498691146271,
"offset": [
2023.9183970432728,
500.497443710502
]
},
"frontendVersion": "1.37.10",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}