Files
wildminder-ComfyUI-Chatterbox/example_workflows/ChatterboxTTS-workflow.json
T
2026-10-11 20:13:00 +03:00

1003 lines
19 KiB
JSON

{
"id": "dba002a2-22d7-4050-a716-4d7196a0d14b",
"revision": 0,
"last_node_id": 47,
"last_link_id": 84,
"nodes": [
{
"id": 30,
"type": "ChatterboxVC",
"pos": [
250,
20
],
"size": [
390,
320
],
"flags": {},
"order": 5,
"mode": 4,
"inputs": [
{
"name": "source_audio",
"type": "AUDIO",
"link": 54
},
{
"name": "target_voice_audio",
"shape": 7,
"type": "AUDIO",
"link": 55
}
],
"outputs": [
{
"name": "converted_audio",
"type": "AUDIO",
"links": [
58
]
}
],
"properties": {
"Node name for S&R": "ChatterboxVC",
"cnr_id": "ComfyUI-ChatterboxTTS",
"ver": "8fc60925cbab607e0f08e0d418c4504e0fcd4842"
},
"widgets_values": [
"chatterbox",
10,
1,
0.7,
false,
"default",
"auto",
"sage",
1,
30,
"smart"
],
"widgets_values_named": {
"model_pack_name": "chatterbox",
"n_timesteps": 10,
"temperature": 1,
"flow_cfg_scale": 0.7,
"use_watermark": false,
"device": "default",
"dtype": "auto",
"attention_mode": "sage",
"refinement_passes": 1,
"max_chunk_duration": 30,
"chunk_method": "smart"
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 31,
"type": "LoadAudio",
"pos": [
710,
450
],
"size": [
370,
170
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
54,
70,
71,
76,
84
]
}
],
"title": "Source Voice",
"properties": {
"Node name for S&R": "LoadAudio",
"cnr_id": "comfy-core",
"ver": "0.3.52",
"ue_properties": {
"widget_ue_connectable": {
"audio": true,
"audioUI": true,
"upload": true
},
"version": "7.0.1"
}
},
"widgets_values": [
"female_daenerys.mp3",
null
],
"widgets_values_named": {
"audio": "female_daenerys.mp3",
"upload": null
},
"color": "#332922",
"bgcolor": "#593930"
},
{
"id": 32,
"type": "LoadAudio",
"pos": [
260,
450
],
"size": [
370,
170
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
55,
77
]
}
],
"title": "Target Voice",
"properties": {
"Node name for S&R": "LoadAudio",
"cnr_id": "comfy-core",
"ver": "0.3.52",
"ue_properties": {
"widget_ue_connectable": {
"audio": true,
"audioUI": true,
"upload": true
},
"version": "7.0.1"
}
},
"widgets_values": [
"male_stewie.mp3",
null
],
"widgets_values_named": {
"audio": "male_stewie.mp3",
"upload": null
},
"color": "#332922",
"bgcolor": "#593930"
},
{
"id": 33,
"type": "SaveAudioAdvanced",
"pos": [
1650,
30
],
"size": [
270,
150
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 68
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveAudioAdvanced"
},
"widgets_values": [
"audio/chatterbox",
"flac"
],
"widgets_values_named": {
"filename_prefix": "audio/chatterbox",
"format": "flac"
}
},
{
"id": 34,
"type": "SaveAudioAdvanced",
"pos": [
680,
20
],
"size": [
270,
150
],
"flags": {},
"order": 12,
"mode": 4,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 58
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveAudioAdvanced"
},
"widgets_values": [
"audio/chatterbox",
"flac"
],
"widgets_values_named": {
"filename_prefix": "audio/chatterbox",
"format": "flac"
}
},
{
"id": 36,
"type": "ChatterboxTTS",
"pos": [
1210,
20
],
"size": [
400,
550
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "audio_prompt",
"shape": 7,
"type": "AUDIO",
"link": 84
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
68
]
}
],
"properties": {
"Node name for S&R": "ChatterboxTTS",
"cnr_id": "ComfyUI-ChatterboxTTS",
"ver": "8fc60925cbab607e0f08e0d418c4504e0fcd4842"
},
"widgets_values": [
"chatterbox",
"I can't believe you did it again. I waited for two hours. Two hours! Not a single call, not a text. Do you have any idea how embarrassing that was, just sitting there alone?",
1000,
0.7,
0.5,
0.8,
0.5,
1.2,
0.05,
1,
42,
"fixed",
false,
"default",
"auto",
"sdpa",
1000,
true,
10,
1
],
"widgets_values_named": {
"model_pack_name": "chatterbox",
"text": "I can't believe you did it again. I waited for two hours. Two hours! Not a single call, not a text. Do you have any idea how embarrassing that was, just sitting there alone?",
"max_new_tokens": 1000,
"flow_cfg_scale": 0.7,
"exaggeration": 0.5,
"temperature": 0.8,
"cfg_weight": 0.5,
"repetition_penalty": 1.2,
"min_p": 0.05,
"top_p": 1,
"seed": 42,
"control_after_generate": "fixed",
"use_watermark": false,
"device": "default",
"dtype": "auto",
"attention_mode": "sdpa",
"top_k": 1000,
"normalize_loudness": true,
"num_steps": 10,
"cfg_scale": 1
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 37,
"type": "ChatterboxMTLTTS",
"pos": [
1190,
810
],
"size": [
400,
480
],
"flags": {},
"order": 2,
"mode": 4,
"inputs": [
{
"name": "audio_prompt",
"shape": 7,
"type": "AUDIO",
"link": 70
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
81
]
}
],
"properties": {
"Node name for S&R": "ChatterboxMTLTTS"
},
"widgets_values": [
"chatterbox-multilingual-zh-cmn",
"t3_23lang.safetensors",
"zh",
"以文化滋养精神家园——习近平文化思想引领文化强国建设迈出新步伐",
0.5,
0.8,
0.5,
1.2,
0.05,
1,
660161351559885,
"fixed",
false,
"default",
"auto",
"sage",
"hmm ,, {seg} hmm ,,"
],
"widgets_values_named": {
"model_pack_name": "chatterbox-multilingual-zh-cmn",
"model_version": "t3_23lang.safetensors",
"language": "zh",
"text": "以文化滋养精神家园——习近平文化思想引领文化强国建设迈出新步伐",
"exaggeration": 0.5,
"temperature": 0.8,
"cfg_weight": 0.5,
"repetition_penalty": 1.2,
"min_p": 0.05,
"top_p": 1,
"seed": 660161351559885,
"control_after_generate": "fixed",
"use_watermark": false,
"device": "default",
"dtype": "auto",
"attention_mode": "sage",
"crash_protection_template": "hmm ,, {seg} hmm ,,"
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 38,
"type": "ChatterboxDialog",
"pos": [
240,
810
],
"size": [
400,
500
],
"flags": {},
"order": 6,
"mode": 4,
"inputs": [
{
"name": "speaker_A_Audio",
"type": "AUDIO",
"link": 76
},
{
"name": "speaker_B_Audio",
"type": "AUDIO",
"link": 77
},
{
"name": "speaker_C_Audio",
"shape": 7,
"type": "AUDIO",
"link": null
},
{
"name": "speaker_D_Audio",
"shape": 7,
"type": "AUDIO",
"link": null
}
],
"outputs": [
{
"name": "dialog_audio",
"type": "AUDIO",
"links": [
78
]
},
{
"name": "speaker_a_audio",
"type": "AUDIO",
"links": null
},
{
"name": "speaker_b_audio",
"type": "AUDIO",
"links": null
},
{
"name": "speaker_c_audio",
"type": "AUDIO",
"links": null
},
{
"name": "speaker_d_audio",
"type": "AUDIO",
"links": null
},
{
"name": "message",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "ChatterboxDialog"
},
"widgets_values": [
"chatterbox",
"t3_mtl23ls_v3.safetensors",
"en",
"SPEAKER A: The first line of the subtitle file.\nSPEAKER B: The second line, three and a half seconds long.\nSPEAKER A: And a third to finish with.",
0.5,
0.5,
0.8,
401053518396655,
"randomize",
false,
"default",
"auto",
"sdpa",
"hmm ,, {seg} hmm ,,"
],
"widgets_values_named": {
"model_pack_name": "chatterbox",
"model_version": "t3_mtl23ls_v3.safetensors",
"language": "en",
"dialog_text": "SPEAKER A: The first line of the subtitle file.\nSPEAKER B: The second line, three and a half seconds long.\nSPEAKER A: And a third to finish with.",
"exaggeration": 0.5,
"cfg_weight": 0.5,
"temperature": 0.8,
"seed": 401053518396655,
"control_after_generate": "randomize",
"use_watermark": false,
"device": "default",
"dtype": "auto",
"attention_mode": "sdpa",
"crash_protection_template": "hmm ,, {seg} hmm ,,"
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 39,
"type": "SaveAudioAdvanced",
"pos": [
720,
1500
],
"size": [
270,
150
],
"flags": {},
"order": 8,
"mode": 4,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 72
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveAudioAdvanced"
},
"widgets_values": [
"audio/chatterbox",
"flac"
],
"widgets_values_named": {
"filename_prefix": "audio/chatterbox",
"format": "flac"
}
},
{
"id": 40,
"type": "ChatterboxSRT",
"pos": [
260,
1500
],
"size": [
400,
690
],
"flags": {},
"order": 3,
"mode": 4,
"inputs": [
{
"name": "audio_prompt",
"shape": 7,
"type": "AUDIO",
"link": 71
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
72
]
},
{
"name": "generation_info",
"type": "STRING",
"links": [
79
]
},
{
"name": "timing_report",
"type": "STRING",
"links": [
80
]
},
{
"name": "Adjusted_SRT",
"type": "STRING",
"links": []
}
],
"properties": {
"Node name for S&R": "ChatterboxSRT"
},
"widgets_values": [
"chatterbox",
"1\n00:00:00,000 --> 00:00:03,000\nThe first line of the subtitle file.\n\n2\n00:00:03,000 --> 00:00:09,500\nThe second line, three and a half seconds long.\n\n3\n00:00:09,500 --> 00:00:15,000\nAnd a third to finish with.\n",
"smart_natural",
1000,
0.7,
0.5,
0.8,
42,
"fixed",
false,
2,
1,
0.5,
0.01,
"default",
"auto",
"sdpa",
"hmm ,, {seg} hmm ,,"
],
"widgets_values_named": {
"model_pack_name": "chatterbox",
"srt_content": "1\n00:00:00,000 --> 00:00:03,000\nThe first line of the subtitle file.\n\n2\n00:00:03,000 --> 00:00:09,500\nThe second line, three and a half seconds long.\n\n3\n00:00:09,500 --> 00:00:15,000\nAnd a third to finish with.\n",
"timing_mode": "smart_natural",
"max_new_tokens": 1000,
"flow_cfg_scale": 0.7,
"exaggeration": 0.5,
"temperature": 0.8,
"seed": 42,
"control_after_generate": "fixed",
"use_watermark": false,
"timing_tolerance": 2,
"max_stretch_ratio": 1,
"min_stretch_ratio": 0.5,
"fade_for_StretchToFit": 0.01,
"device": "default",
"dtype": "auto",
"attention_mode": "sdpa",
"crash_protection_template": "hmm ,, {seg} hmm ,,"
}
},
{
"id": 44,
"type": "SaveAudioAdvanced",
"pos": [
700,
810
],
"size": [
270,
150
],
"flags": {},
"order": 13,
"mode": 4,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 78
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveAudioAdvanced"
},
"widgets_values": [
"audio/chatterbox",
"flac"
],
"widgets_values_named": {
"filename_prefix": "audio/chatterbox",
"format": "flac"
}
},
{
"id": 45,
"type": "PreviewAny",
"pos": [
720,
1730
],
"size": [
260,
160
],
"flags": {},
"order": 9,
"mode": 4,
"inputs": [
{
"name": "source",
"type": "*",
"link": 79
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "PreviewAny"
},
"widgets_values": [],
"widgets_values_named": {}
},
{
"id": 46,
"type": "PreviewAny",
"pos": [
720,
1950
],
"size": [
260,
160
],
"flags": {},
"order": 10,
"mode": 4,
"inputs": [
{
"name": "source",
"type": "*",
"link": 80
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": []
}
],
"properties": {
"Node name for S&R": "PreviewAny"
},
"widgets_values": [],
"widgets_values_named": {}
},
{
"id": 47,
"type": "SaveAudioAdvanced",
"pos": [
1670,
820
],
"size": [
270,
150
],
"flags": {},
"order": 7,
"mode": 4,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 81
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": []
}
],
"properties": {
"Node name for S&R": "SaveAudioAdvanced"
},
"widgets_values": [
"audio/chatterbox",
"flac"
],
"widgets_values_named": {
"filename_prefix": "audio/chatterbox",
"format": "flac"
}
}
],
"links": [
[
54,
31,
0,
30,
0,
"AUDIO"
],
[
55,
32,
0,
30,
1,
"AUDIO"
],
[
70,
31,
0,
37,
0,
"AUDIO"
],
[
71,
31,
0,
40,
0,
"AUDIO"
],
[
76,
31,
0,
38,
0,
"AUDIO"
],
[
77,
32,
0,
38,
1,
"AUDIO"
],
[
79,
40,
1,
45,
0,
"STRING"
],
[
80,
40,
2,
46,
0,
"STRING"
],
[
84,
31,
0,
36,
0,
"AUDIO"
],
[
68,
36,
0,
33,
0,
"AUDIO"
],
[
58,
30,
0,
34,
0,
"AUDIO"
],
[
72,
40,
0,
39,
0,
"AUDIO"
],
[
78,
38,
0,
44,
0,
"AUDIO"
],
[
81,
37,
0,
47,
0,
"AUDIO"
]
],
"groups": [
{
"id": 1,
"title": "Voice conversion",
"bounding": [
220,
-70,
910,
450
],
"color": "#3f789e",
"flags": {}
},
{
"id": 2,
"title": "Text 2 Voice",
"bounding": [
1180,
-70,
770,
760
],
"color": "#3f789e",
"flags": {}
},
{
"id": 3,
"title": "Group",
"bounding": [
1180,
740,
770,
660
],
"color": "#3f789e",
"flags": {}
},
{
"id": 4,
"title": "Group",
"bounding": [
230,
740,
900,
660
],
"color": "#3f789e",
"flags": {}
},
{
"id": 5,
"title": "Group",
"bounding": [
250,
1430,
750,
770
],
"color": "#3f789e",
"flags": {}
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.7848447621175021,
"offset": [
-8.042732499295383,
137.5873485252725
]
},
"frontendVersion": "1.55.14",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}