AI Text-to-Speech & Voice Cloning for ComfyUI using OpenAudio S1-mini (Fish Audio). Features DualAR Transformer, DAC codec, voice cloning, emotion control tags, Whisper transcription, and per-token progress bars. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
349 lines
6.1 KiB
JSON
349 lines
6.1 KiB
JSON
{
|
|
"id": "5c147db7-9402-4654-a208-d81db2995722",
|
|
"revision": 0,
|
|
"last_node_id": 35,
|
|
"last_link_id": 54,
|
|
"nodes": [
|
|
{
|
|
"id": 34,
|
|
"type": "FL_FishSpeech_Transcribe",
|
|
"pos": [
|
|
-1558.0367469259602,
|
|
-2127.7794654819163
|
|
],
|
|
"size": [
|
|
272.0015625,
|
|
106
|
|
],
|
|
"flags": {},
|
|
"order": 2,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "audio",
|
|
"type": "AUDIO",
|
|
"link": 49
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "transcription",
|
|
"type": "STRING",
|
|
"links": [
|
|
50
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_FishSpeech_Transcribe"
|
|
},
|
|
"widgets_values": [
|
|
"openai/whisper-large-v3-turbo",
|
|
"auto",
|
|
"auto"
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 21,
|
|
"type": "FL_FishSpeech_ReferenceAudio",
|
|
"pos": [
|
|
-1559.9020764707666,
|
|
-2292.290103740347
|
|
],
|
|
"size": [
|
|
275.4993789777918,
|
|
108
|
|
],
|
|
"flags": {},
|
|
"order": 3,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "fs_model",
|
|
"type": "FS_MODEL",
|
|
"link": 33
|
|
},
|
|
{
|
|
"name": "audio",
|
|
"type": "AUDIO",
|
|
"link": 45
|
|
},
|
|
{
|
|
"name": "transcript",
|
|
"type": "STRING",
|
|
"widget": {
|
|
"name": "transcript"
|
|
},
|
|
"link": 50
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "fs_reference",
|
|
"type": "FS_REFERENCE",
|
|
"links": [
|
|
53
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_FishSpeech_ReferenceAudio"
|
|
},
|
|
"widgets_values": [
|
|
""
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 20,
|
|
"type": "FL_FishSpeech_ModelLoader",
|
|
"pos": [
|
|
-1920.8141903172211,
|
|
-2375.8077779590035
|
|
],
|
|
"size": [
|
|
283.8968694424476,
|
|
130
|
|
],
|
|
"flags": {},
|
|
"order": 0,
|
|
"mode": 0,
|
|
"inputs": [],
|
|
"outputs": [
|
|
{
|
|
"name": "fs_model",
|
|
"type": "FS_MODEL",
|
|
"links": [
|
|
33,
|
|
52
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_FishSpeech_ModelLoader"
|
|
},
|
|
"widgets_values": [
|
|
"auto",
|
|
"bfloat16",
|
|
true,
|
|
false
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 26,
|
|
"type": "LoadAudio",
|
|
"pos": [
|
|
-1920.3127493809948,
|
|
-2192.5391746417204
|
|
],
|
|
"size": [
|
|
282.798828125,
|
|
136
|
|
],
|
|
"flags": {},
|
|
"order": 1,
|
|
"mode": 0,
|
|
"inputs": [],
|
|
"outputs": [
|
|
{
|
|
"name": "AUDIO",
|
|
"type": "AUDIO",
|
|
"links": [
|
|
45,
|
|
49
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"cnr_id": "comfy-core",
|
|
"ver": "0.12.2",
|
|
"Node name for S&R": "LoadAudio"
|
|
},
|
|
"widgets_values": [
|
|
"chunk_035.mp3",
|
|
null,
|
|
null
|
|
]
|
|
},
|
|
{
|
|
"id": 35,
|
|
"type": "FL_FishSpeech_TTS",
|
|
"pos": [
|
|
-1249.0463040827638,
|
|
-2373.0131401698054
|
|
],
|
|
"size": [
|
|
370.4508019725772,
|
|
347.4578028925275
|
|
],
|
|
"flags": {},
|
|
"order": 4,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "fs_model",
|
|
"type": "FS_MODEL",
|
|
"link": 52
|
|
},
|
|
{
|
|
"name": "fs_reference",
|
|
"shape": 7,
|
|
"type": "FS_REFERENCE",
|
|
"link": 53
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "audio",
|
|
"type": "AUDIO",
|
|
"links": [
|
|
54
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_FishSpeech_TTS"
|
|
},
|
|
"widgets_values": [
|
|
"(annoyed) It's a one-time cost; subsequent generations will be faster. If the compilation delay is annoying.",
|
|
1553086716,
|
|
"randomize",
|
|
1,
|
|
0.9,
|
|
30,
|
|
1.1,
|
|
512,
|
|
0
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 24,
|
|
"type": "SaveAudioMP3",
|
|
"pos": [
|
|
-1255.3044660528758,
|
|
-2563.0055291837
|
|
],
|
|
"size": [
|
|
383.0059829895408,
|
|
136
|
|
],
|
|
"flags": {},
|
|
"order": 5,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "audio",
|
|
"type": "AUDIO",
|
|
"link": 54
|
|
}
|
|
],
|
|
"outputs": [],
|
|
"properties": {
|
|
"cnr_id": "comfy-core",
|
|
"ver": "0.12.2",
|
|
"Node name for S&R": "SaveAudioMP3"
|
|
},
|
|
"widgets_values": [
|
|
"audio/ComfyUI",
|
|
"V0"
|
|
]
|
|
}
|
|
],
|
|
"links": [
|
|
[
|
|
33,
|
|
20,
|
|
0,
|
|
21,
|
|
0,
|
|
"FS_MODEL"
|
|
],
|
|
[
|
|
45,
|
|
26,
|
|
0,
|
|
21,
|
|
1,
|
|
"AUDIO"
|
|
],
|
|
[
|
|
49,
|
|
26,
|
|
0,
|
|
34,
|
|
0,
|
|
"AUDIO"
|
|
],
|
|
[
|
|
50,
|
|
34,
|
|
0,
|
|
21,
|
|
2,
|
|
"STRING"
|
|
],
|
|
[
|
|
52,
|
|
20,
|
|
0,
|
|
35,
|
|
0,
|
|
"FS_MODEL"
|
|
],
|
|
[
|
|
53,
|
|
21,
|
|
0,
|
|
35,
|
|
1,
|
|
"FS_REFERENCE"
|
|
],
|
|
[
|
|
54,
|
|
35,
|
|
0,
|
|
24,
|
|
0,
|
|
"AUDIO"
|
|
]
|
|
],
|
|
"groups": [
|
|
{
|
|
"id": 1,
|
|
"title": "Group",
|
|
"bounding": [
|
|
-1930.8141903172211,
|
|
-2636.6055291837,
|
|
1072.9928584701627,
|
|
628.7508919984176
|
|
],
|
|
"color": "#3f789e",
|
|
"font_size": 24,
|
|
"flags": {}
|
|
}
|
|
],
|
|
"config": {},
|
|
"extra": {
|
|
"workflowRendererVersion": "LG",
|
|
"ds": {
|
|
"scale": 0.9229599817706431,
|
|
"offset": [
|
|
2652.5825364648717,
|
|
3014.096905763467
|
|
]
|
|
},
|
|
"frontendVersion": "1.37.11",
|
|
"VHS_latentpreview": false,
|
|
"VHS_latentpreviewrate": 0,
|
|
"VHS_MetadataImage": true,
|
|
"VHS_KeepIntermediate": true
|
|
},
|
|
"version": 0.4
|
|
} |