VoiceGate / workflows /voicegate_ui.json
YanTianlong's picture
Add VoiceGate workflow assets and TODO
5277693
Raw
History Blame Contribute Delete
98.6 kB
{
"id": "84fa3ca3-0dc0-4776-9191-b1f82b6d0f98",
"revision": 0,
"last_node_id": 268,
"last_link_id": 316,
"nodes": [
{
"id": 61,
"type": "easy showAnything",
"pos": [
3405.466552734375,
1242.3624267578125
],
"size": [
264.173583984375,
244.0182647705078
],
"flags": {},
"order": 41,
"mode": 0,
"inputs": [
{
"label": "anything",
"name": "anything",
"shape": 7,
"type": "*",
"link": 104
}
],
"outputs": [
{
"label": "output",
"name": "output",
"type": "*"
}
],
"properties": {
"Node name for S&R": "easy showAnything",
"widget_ue_connectable": {}
},
"widgets_values": [
"1\n00:00:00,000 --> 00:00:04,000\n我相信你在各种内容下面应该都见过这样一句类似的评论\n\n2\n00:00:04,240 --> 00:00:04,960\n那几个月之前\n\n3\n00:00:04,960 --> 00:00:06,879\n其实大家把这个当成一种调侃了\n\n4\n00:00:06,879 --> 00:00:07,679\n是一种梗\n\n5\n00:00:07,679 --> 00:00:07,919\n对吧\n\n6\n00:00:08,160 --> 00:00:09,359\n你看到太离谱的东西\n\n7\n00:00:09,439 --> 00:00:10,320\n你会说\n\n8\n00:00:10,320 --> 00:00:10,800\n“哎呀\n\n9\n00:00:10,800 --> 00:00:12,560\n这是AI或者AI太好用了\n\n10\n00:00:12,560 --> 00:00:12,960\n家人\n\n11\n00:00:13,359 --> 00:00:14,240\n”但有意思的就是\n\n12\n00:00:14,240 --> 00:00:15,359\n只过了短短几个月\n\n13\n00:00:15,519 --> 00:00:19,519\n你会发现现在这句“这是AI嘛”背后的情绪它变化了\n\n14\n00:00:19,839 --> 00:00:21,280\n因为AI它又变强了\n\n"
]
},
{
"id": 121,
"type": "SetNode",
"pos": [
3027.077392578125,
1938.8333740234375
],
"size": [
210,
60
],
"flags": {},
"order": 53,
"mode": 0,
"inputs": [
{
"label": "LIST",
"name": "LIST",
"type": "LIST",
"link": 166
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_forced_aligns",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "forced_aligns",
"widget_ue_connectable": {}
},
"widgets_values": [
"forced_aligns"
]
},
{
"id": 122,
"type": "SetNode",
"pos": [
3031.775634765625,
2067.592041015625
],
"size": [
210,
58
],
"flags": {},
"order": 54,
"mode": 0,
"inputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"link": 167
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_text",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "text",
"widget_ue_connectable": {}
},
"widgets_values": [
"text"
]
},
{
"id": 123,
"type": "SetNode",
"pos": [
3030.826416015625,
2188.187744140625
],
"size": [
210,
58
],
"flags": {},
"order": 55,
"mode": 0,
"inputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"link": 168
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_language",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "language",
"widget_ue_connectable": {}
},
"widgets_values": [
"language"
]
},
{
"id": 124,
"type": "GetNode",
"pos": [
3154.44189453125,
988.6742553710938
],
"size": [
210,
60
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "LIST",
"name": "LIST",
"type": "LIST",
"links": [
169
]
}
],
"title": "Get_forced_aligns",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"forced_aligns"
]
},
{
"id": 126,
"type": "GetNode",
"pos": [
3150.58349609375,
1269.900146484375
],
"size": [
210,
58
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
171
]
}
],
"title": "Get_language",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"language"
]
},
{
"id": 109,
"type": "ReplaceText",
"pos": [
3926.60693359375,
1252.896728515625
],
"size": [
270,
106
],
"flags": {},
"order": 38,
"mode": 0,
"inputs": [
{
"label": "texts",
"name": "texts",
"type": "STRING",
"widget": {
"name": "texts"
},
"link": 149
},
{
"label": "find",
"name": "find",
"type": "STRING",
"widget": {
"name": "find"
}
},
{
"label": "replace",
"name": "replace",
"type": "STRING",
"widget": {
"name": "replace"
},
"link": 151
}
],
"outputs": [
{
"label": "texts",
"name": "texts",
"type": "STRING",
"links": [
150
]
}
],
"properties": {
"Node name for S&R": "ReplaceText",
"widget_ue_connectable": {}
},
"widgets_values": [
"",
"[Language]",
"English"
]
},
{
"id": 127,
"type": "SetNode",
"pos": [
4682.775390625,
1325.0826416015625
],
"size": [
210,
60
],
"flags": {},
"order": 59,
"mode": 0,
"inputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"link": 172
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_Translated SRT",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Translated SRT",
"widget_ue_connectable": {}
},
"widgets_values": [
"Translated SRT"
]
},
{
"id": 125,
"type": "GetNode",
"pos": [
3157.4619140625,
1134.2364501953125
],
"size": [
210,
58
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
170
]
}
],
"title": "Get_text",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"text"
]
},
{
"id": 31,
"type": "VoiceBridgeASRLoader",
"pos": [
2285.4912109375,
1969.413330078125
],
"size": [
285.716796875,
226
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"label": "repo_id",
"name": "repo_id",
"type": "COMBO",
"widget": {
"name": "repo_id"
}
},
{
"label": "precision",
"name": "precision",
"type": "COMBO",
"widget": {
"name": "precision"
}
},
{
"label": "attention",
"name": "attention",
"type": "COMBO",
"widget": {
"name": "attention"
}
},
{
"label": "max_new_tokens",
"name": "max_new_tokens",
"shape": 7,
"type": "INT",
"widget": {
"name": "max_new_tokens"
}
},
{
"label": "forced_aligner",
"name": "forced_aligner",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "forced_aligner"
}
}
],
"outputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"links": [
208,
209
]
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRLoader",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"forced_aligner": true,
"max_new_tokens": true,
"precision": true,
"attention": true
}
},
"widgets_values": [
"Qwen/Qwen3-ASR-1.7B",
"bf16",
"flash_attention_2",
1024,
"Qwen/Qwen3-ForcedAligner-0.6B"
]
},
{
"id": 118,
"type": "SetNode",
"pos": [
3022.862548828125,
1773.826416015625
],
"size": [
210,
60
],
"flags": {},
"order": 60,
"mode": 0,
"inputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"link": 163
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_Reference text",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Reference text",
"widget_ue_connectable": {}
},
"widgets_values": [
"Reference text"
]
},
{
"id": 107,
"type": "easy showAnything",
"pos": [
4673.2158203125,
978.5053100585938
],
"size": [
339.7774963378906,
289.5758972167969
],
"flags": {},
"order": 58,
"mode": 0,
"inputs": [
{
"label": "anything",
"name": "anything",
"shape": 7,
"type": "*",
"link": 147
}
],
"outputs": [
{
"label": "output",
"name": "output",
"type": "*"
}
],
"properties": {
"Node name for S&R": "easy showAnything",
"widget_ue_connectable": {}
},
"widgets_values": [
"1\n00:00:00,000 --> 00:00:04,000\nI bet you've seen a comment like this under all kinds of content.\n\n2\n00:00:04,240 --> 00:00:04,960\nA few months ago,\n\n3\n00:00:04,960 --> 00:00:06,879\neveryone used it as a joke.\n\n4\n00:00:06,879 --> 00:00:07,679\nIt was a meme.\n\n5\n00:00:07,679 --> 00:00:07,919\nRight?\n\n6\n00:00:08,160 --> 00:00:09,359\nYou see something absurd.\n\n7\n00:00:09,439 --> 00:00:10,320\nYou'd say,\n\n8\n00:00:10,320 --> 00:00:10,800\n\"Ah,\n\n9\n00:00:10,800 --> 00:00:12,560\nmust be AI, or AI is too good.\n\n10\n00:00:12,560 --> 00:00:12,960\nBro.\"\n\n11\n00:00:13,359 --> 00:00:14,240\nBut the interesting thing is,\n\n12\n00:00:14,240 --> 00:00:15,359\njust a few months later,\n\n13\n00:00:15,519 --> 00:00:19,519\nnow the emotion behind \"Is this AI?\" has changed.\n\n14\n00:00:19,839 --> 00:00:21,280\nBecause AI has gotten even stronger."
]
},
{
"id": 117,
"type": "SetNode",
"pos": [
3005.62646484375,
1654.7073974609375
],
"size": [
218.11972045898438,
60
],
"flags": {},
"order": 52,
"mode": 0,
"inputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"link": 162
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_Original reference audio",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Original reference audio",
"widget_ue_connectable": {}
},
"widgets_values": [
"Original reference audio"
]
},
{
"id": 149,
"type": "Note",
"pos": [
2257.952880859375,
989.4893188476562
],
"size": [
287.9577941894531,
100.70368194580078
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": [
"加载你的原始音频,他会自动分离出纯人类的声音\n\nLoad your original audio and it will automatically separate out the pure human voices."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 96,
"type": "MelBandRoFormerModelLoader",
"pos": [
2559.361083984375,
1033.3271484375
],
"size": [
256.2164001464844,
58
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"label": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
}
}
],
"outputs": [
{
"label": "model",
"name": "model",
"type": "MELROFORMERMODEL",
"links": [
137
]
}
],
"properties": {
"Node name for S&R": "MelBandRoFormerModelLoader",
"widget_ue_connectable": {}
},
"widgets_values": [
"MelBandRoFormer_comfy/MelBandRoformer_fp32.safetensors"
]
},
{
"id": 164,
"type": "SetNode",
"pos": [
2839.226806640625,
1224.4898681640625
],
"size": [
223.57479858398438,
58
],
"flags": {},
"order": 49,
"mode": 0,
"inputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"link": 199
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_Ambient sound",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Ambient sound",
"widget_ue_connectable": {}
},
"widgets_values": [
"Ambient sound"
]
},
{
"id": 115,
"type": "SetNode",
"pos": [
2840.291259765625,
1104.8675537109375
],
"size": [
223.57479858398438,
60
],
"flags": {},
"order": 48,
"mode": 0,
"inputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"link": 159
}
],
"outputs": [
{
"label": "*",
"name": "*",
"type": "*"
}
],
"title": "Set_Separated human voices",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Separated human voices",
"widget_ue_connectable": {}
},
"widgets_values": [
"Separated human voices"
]
},
{
"id": 33,
"type": "VoiceBridgeASRTranscribe",
"pos": [
2613.611328125,
1966.503173828125
],
"size": [
339.7463073730469,
196
],
"flags": {},
"order": 40,
"mode": 0,
"inputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"link": 209
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 161
},
{
"label": "language",
"name": "language",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "language"
}
},
{
"label": "context",
"name": "context",
"shape": 7,
"type": "STRING",
"widget": {
"name": "context"
}
},
{
"label": "return_timestamps",
"name": "return_timestamps",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "return_timestamps"
}
},
{
"label": "model",
"name": "model",
"type": "QWEN3_ASR_MODEL"
}
],
"outputs": [
{
"label": "forced_aligns",
"name": "forced_aligns",
"type": "LIST",
"links": [
166
]
},
{
"label": "text",
"name": "text",
"type": "STRING",
"links": [
167
]
},
{
"label": "language",
"name": "language",
"type": "STRING",
"links": [
168
]
},
{
"label": "timestamps",
"name": "timestamps",
"type": "STRING"
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRTranscribe",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"context": true,
"language": true,
"return_timestamps": true
}
},
"widgets_values": [
"auto",
"",
true
]
},
{
"id": 36,
"type": "GenerateSRT",
"pos": [
3394.440185546875,
988.6742553710938
],
"size": [
272.1141662597656,
187.92388916015625
],
"flags": {},
"order": 29,
"mode": 0,
"inputs": [
{
"label": "forced_aligns",
"name": "forced_aligns",
"type": "LIST",
"link": 169
},
{
"label": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 170
},
{
"label": "language",
"name": "language",
"type": "STRING",
"widget": {
"name": "language"
},
"link": 171
},
{
"label": "save_srt",
"name": "save_srt",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "save_srt"
}
},
{
"label": "filename_prefix",
"name": "filename_prefix",
"shape": 7,
"type": "STRING",
"widget": {
"name": "filename_prefix"
}
}
],
"outputs": [
{
"label": "srt_string",
"name": "srt_string",
"type": "STRING",
"links": [
104,
146
]
}
],
"properties": {
"Node name for S&R": "GenerateSRT",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"text": true
}
},
"widgets_values": [
"",
"",
true,
"VoiceBridge/subtitle"
]
},
{
"id": 108,
"type": "CR Text",
"pos": [
3750.109375,
984.0011596679688
],
"size": [
400,
200
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"label": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
}
}
],
"outputs": [
{
"label": "text",
"name": "text",
"type": "*",
"links": [
149
]
},
{
"label": "show_help",
"name": "show_help",
"type": "STRING"
}
],
"properties": {
"Node name for S&R": "CR Text",
"widget_ue_connectable": {}
},
"widgets_values": [
"You are a professional subtitle translator. Please translate all the subtitles in this SRT file into natural, spoken [Language]. Keep each timestamp exactly the same. For each subtitle line, use the shortest possible phrasing that still captures the original meaning (it doesn't have to be a direct translation, just convey the correct idea). Output the content directly in SRT format, without any explanation or descriptive text."
]
},
{
"id": 128,
"type": "Note",
"pos": [
2280.927490234375,
1437.8023681640625
],
"size": [
210,
88
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": [
" ↑↑↑↑\n 在这里输入你的目标语言\n\n Input your target language here"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 215,
"type": "MelBandRoFormerSampler",
"pos": [
2680.94921875,
3011.865966796875
],
"size": [
231.27206420898438,
46
],
"flags": {
"collapsed": false
},
"order": 31,
"mode": 4,
"inputs": [
{
"label": "model",
"name": "model",
"type": "MELROFORMERMODEL",
"link": 254
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 256
}
],
"outputs": [
{
"label": "vocals",
"name": "vocals",
"type": "AUDIO",
"links": [
255
]
},
{
"label": "instruments",
"name": "instruments",
"type": "AUDIO",
"links": []
}
],
"properties": {
"Node name for S&R": "MelBandRoFormerSampler",
"cnr_id": "ComfyUI-MelBandRoFormer",
"ver": "b40e263224778ec417114d91d8b3b39934e30de5",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.5.2"
},
"widget_ue_connectable": {}
},
"widgets_values": []
},
{
"id": 198,
"type": "VoiceBridgeASRLoader",
"pos": [
2965.889892578125,
2995.493408203125
],
"size": [
285.716796875,
226
],
"flags": {},
"order": 8,
"mode": 4,
"inputs": [
{
"label": "repo_id",
"name": "repo_id",
"type": "COMBO",
"widget": {
"name": "repo_id"
}
},
{
"label": "precision",
"name": "precision",
"type": "COMBO",
"widget": {
"name": "precision"
}
},
{
"label": "attention",
"name": "attention",
"type": "COMBO",
"widget": {
"name": "attention"
}
},
{
"label": "max_new_tokens",
"name": "max_new_tokens",
"shape": 7,
"type": "INT",
"widget": {
"name": "max_new_tokens"
}
},
{
"label": "forced_aligner",
"name": "forced_aligner",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "forced_aligner"
}
}
],
"outputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"links": [
243
]
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRLoader",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"forced_aligner": true,
"max_new_tokens": true,
"precision": true,
"attention": true
}
},
"widgets_values": [
"Qwen/Qwen3-ASR-1.7B",
"bf16",
"flash_attention_2",
1024,
"Qwen/Qwen3-ForcedAligner-0.6B"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 202,
"type": "VoiceBridgeASRTranscribe",
"pos": [
3322.212890625,
2996.067138671875
],
"size": [
339.7463073730469,
196
],
"flags": {},
"order": 44,
"mode": 4,
"inputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"link": 243
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 255
},
{
"label": "language",
"name": "language",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "language"
}
},
{
"label": "context",
"name": "context",
"shape": 7,
"type": "STRING",
"widget": {
"name": "context"
}
},
{
"label": "return_timestamps",
"name": "return_timestamps",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "return_timestamps"
}
},
{
"label": "model",
"name": "model",
"type": "QWEN3_ASR_MODEL"
}
],
"outputs": [
{
"label": "forced_aligns",
"name": "forced_aligns",
"type": "LIST",
"links": [
239
]
},
{
"label": "text",
"name": "text",
"type": "STRING",
"links": [
240
]
},
{
"label": "language",
"name": "language",
"type": "STRING",
"links": [
241
]
},
{
"label": "timestamps",
"name": "timestamps",
"type": "STRING"
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRTranscribe",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"context": true,
"language": true,
"return_timestamps": true
}
},
"widgets_values": [
"auto",
"",
true
],
"color": "#332922",
"bgcolor": "#593930"
},
{
"id": 200,
"type": "GenerateSRT",
"pos": [
3712.6494140625,
2997.569580078125
],
"size": [
272.1141662597656,
187.92388916015625
],
"flags": {},
"order": 56,
"mode": 4,
"inputs": [
{
"label": "forced_aligns",
"name": "forced_aligns",
"type": "LIST",
"link": 239
},
{
"label": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 240
},
{
"label": "language",
"name": "language",
"type": "STRING",
"widget": {
"name": "language"
},
"link": 241
},
{
"label": "save_srt",
"name": "save_srt",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "save_srt"
}
},
{
"label": "filename_prefix",
"name": "filename_prefix",
"shape": 7,
"type": "STRING",
"widget": {
"name": "filename_prefix"
}
}
],
"outputs": [
{
"label": "srt_string",
"name": "srt_string",
"type": "STRING",
"links": [
242
]
}
],
"properties": {
"Node name for S&R": "GenerateSRT",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"text": true
}
},
"widgets_values": [
"",
"",
true,
"VoiceBridge/subtitle"
],
"color": "#233",
"bgcolor": "#355"
},
{
"id": 201,
"type": "easy showAnything",
"pos": [
4045.969970703125,
2993.702392578125
],
"size": [
356.7189025878906,
272.81671142578125
],
"flags": {},
"order": 61,
"mode": 4,
"inputs": [
{
"label": "anything",
"name": "anything",
"shape": 7,
"type": "*",
"link": 242
}
],
"outputs": [
{
"label": "output",
"name": "output",
"type": "*"
}
],
"properties": {
"Node name for S&R": "easy showAnything",
"widget_ue_connectable": {}
},
"widgets_values": [
"1\n00:00:00,320 --> 00:00:01,120\nHello 大家好\n\n2\n00:00:01,120 --> 00:00:02,160\n我是Sam\n\n3\n00:00:01,439 --> 00:00:02,160\nFeeling\n\n4\n00:00:02,640 --> 00:00:07,280\n今天给大家介绍一下免魔法、免登录的Codex安装教程\n\n5\n00:00:07,599 --> 00:00:10,720\n首先来说一下为什么我们会选择Codex\n\n6\n00:00:10,800 --> 00:00:14,960\n而不是Cloud Code或者Open Cloud这些Agent\n\n7\n00:00:15,439 --> 00:00:17,199\n首先跟Cloud Code对比的话\n\n8\n00:00:17,199 --> 00:00:18,800\nCodex是开源的\n\n9\n00:00:18,800 --> 00:00:23,920\n可以看到我们这个Github上Codex幺幺一直是开源的\n\n10\n00:00:24,480 --> 00:00:27,839\n虽然说Cloud Code之前的源码被泄露过\n\n11\n00:00:27,839 --> 00:00:32,560\n但是后续的更新在泄露版里面是没法支持的\n\n12\n00:00:32,640 --> 00:00:39,359\n也就是说在泄露的开源版本的Cloud Code里面是没有办法使用我们最新的特性的\n\n13\n00:00:39,840 --> 00:00:40,159\n呃\n\n14\n00:00:40,159 --> 00:00:41,600\nCodex一直是开源的\n\n15\n00:00:41,600 --> 00:00:45,920\n所以开源版本都是支持我们的最新特性的\n\n16\n00:00:46,560 --> 00:00:49,119\n那么在开源Agent里面呢\n\n17\n00:00:49,119 --> 00:00:53,039\n我们还可以选择Open Open Cloud和Hermes Agent\n\n18\n00:00:54,079 --> 00:00:59,920\n但是Open Cloud和Hermes Agent这两个Agent安装都需要命令行\n\n19\n00:01:00,399 --> 00:01:05,519\n没法像Codex一样给出一个安装程序包就可以安装\n\n20\n00:01:06,159 --> 00:01:06,959\n还有一点是\n\n21\n00:01:06,959 --> 00:01:09,280\n如果你本来就是程序员的话\n\n22\n00:01:09,680 --> 00:01:11,200\n你是要正经写代码的\n\n23\n00:01:11,760 --> 00:01:14,480\n那肯定是优先选Cloud Code和Codex\n\n24\n00:01:14,560 --> 00:01:18,719\n而不是Hermes Agent和Open Cloud\n\n25\n00:01:16,959 --> 00:01:20,319\nCodex不仅可以处理代码\n\n26\n00:01:20,319 --> 00:01:23,599\n如果大家是非代码专业的话\n\n27\n00:01:23,840 --> 00:01:27,120\n其实Codex还可以帮我们自动处理很多文档\n\n28\n00:01:27,359 --> 00:01:28,719\n当你用过之后就回不去了\n\n29\n00:01:29,200 --> 00:01:36,400\n还有一点就是Codex现在已经支持了Open Cloud和Hermes Agent里面的记忆和自进化的功能\n\n30\n00:01:36,879 --> 00:01:37,040\n好\n\n31\n00:01:37,040 --> 00:01:41,120\n现在我们来安装一下MacOS端的Codex\n\n32\n00:01:41,120 --> 00:01:44,239\n现在我先把我旧的Codex全部卸载掉\n\n33\n00:01:45,680 --> 00:01:48,000\n保证我们环境是干净的\n\n34\n00:01:49,840 --> 00:01:50,079\n好\n\n35\n00:01:50,159 --> 00:01:51,599\n这里已经卸卸载完了\n\n36\n00:01:52,159 --> 00:01:54,319\n我们先运行这个Codex\n\n37\n00:01:56,319 --> 00:01:59,599\n然后把它拖进应用程序安装一下\n\n38\n00:02:04,000 --> 00:02:04,239\n好\n\n39\n00:02:04,239 --> 00:02:04,959\n安装好了\n\n40\n00:02:06,239 --> 00:02:09,039\n然后我们再安安装这个Codex 大家好\n\n41\n00:02:09,039 --> 00:02:13,599\n这里弹出一个两个程序我们都需要安装的\n\n42\n00:02:14,080 --> 00:02:16,240\n然后我们点击应用程序\n\n43\n00:02:17,120 --> 00:02:19,599\n然后把这两个粘贴过来\n\n44\n00:02:20,319 --> 00:02:21,360\n粘贴到应用程序这里\n\n45\n00:02:22,479 --> 00:02:22,879\n好\n\n46\n00:02:23,120 --> 00:02:23,520\n粘贴完了\n\n47\n00:02:23,599 --> 00:02:25,199\n我们点击运行\n\n48\n00:02:26,400 --> 00:02:26,639\n好\n\n49\n00:02:26,639 --> 00:02:30,080\n可以看到我们这个是显示是文件转换\n\n50\n00:02:30,879 --> 00:02:33,599\n这是我们打开我们的终端\n\n51\n00:02:34,479 --> 00:02:35,280\n稍等片刻\n\n52\n00:02:38,479 --> 00:02:38,719\n好\n\n53\n00:02:38,719 --> 00:02:40,800\n我们终端已经打开出来了\n\n54\n00:02:41,439 --> 00:02:43,520\n然后我们点击一下这个\n\n55\n00:02:43,520 --> 00:02:45,360\n然后把这个终端拖过来这边\n\n56\n00:02:46,000 --> 00:02:46,240\n输\n\n57\n00:02:46,400 --> 00:02:52,000\n然后我们在这里输一个命令x a t t r g c r空格\n\n58\n00:02:52,240 --> 00:02:53,599\n记得这里一定要加一个空格\n\n59\n00:02:54,400 --> 00:02:57,520\n然后我们选中这两个程序\n\n60\n00:02:57,680 --> 00:02:58,479\n把它拖进来\n\n61\n00:02:59,110 --> 00:03:00,070\n然后再点下回车\n\n62\n00:03:00,070 --> 00:03:00,471\n好\n\n63\n00:03:00,790 --> 00:03:03,191\n这里没有报错就说明你已经执行成功了\n\n64\n00:03:03,751 --> 00:03:05,670\n这时候我们再点击一下\n\n65\n00:03:05,830 --> 00:03:06,871\n先把这个取消掉\n\n66\n00:03:07,270 --> 00:03:08,550\n这时候我们再点击一下\n\n67\n00:03:09,830 --> 00:03:11,591\n可以看到我们已经启动起来了\n\n68\n00:03:13,191 --> 00:03:15,270\n我这里调成一个白天模式\n\n69\n00:03:15,911 --> 00:03:18,070\n然后我们点击这个模型提供商\n\n70\n00:03:18,950 --> 00:03:19,591\n添加\n\n71\n00:03:20,950 --> 00:03:22,471\n提供商我们用 D C\n\n72\n00:03:23,991 --> 00:03:25,591\n因为前几天 D C\n\n73\n00:03:27,350 --> 00:03:32,471\n因为昨天 D C 刚刚宣布它的 V4 Pro 永久降价了\n\n74\n00:03:32,871 --> 00:03:34,711\n一直都是保持二点五折\n\n75\n00:03:35,991 --> 00:03:38,151\n我们这里选择选 A P I\n\n76\n00:03:38,871 --> 00:03:40,230\n测试模型的话\n\n77\n00:03:40,950 --> 00:03:47,431\n我们随便填一个 D C V4 的 Flash 吧\n\n78\n00:03:48,871 --> 00:03:49,911\n注意这里一定要小写\n\n79\n00:03:51,431 --> 00:03:58,151\n然后这个 Base URL 就是我们 D C 官方的一个地址\n\n80\n00:03:59,830 --> 00:04:05,350\nA P I key 也是从我们官方的 D C A P I 的平台获取\n\n81\n00:04:06,151 --> 00:04:09,270\n然后我们这里一定要选择这个 Chat 模式\n\n82\n00:04:10,631 --> 00:04:11,350\n保存一下\n\n83\n00:04:14,390 --> 00:04:17,190\n然后我们这里选择使用我们刚刚配置好的\n\n84\n00:04:17,911 --> 00:04:19,190\n我们在这里测试一下\n\n85\n00:04:20,071 --> 00:04:20,310\n好\n\n86\n00:04:20,310 --> 00:04:21,110\n已经测试成功\n\n87\n00:04:21,110 --> 00:04:22,550\n说明我们这个配置完成\n\n88\n00:04:23,670 --> 00:04:25,271\n这时候我们再回到这里\n\n89\n00:04:25,430 --> 00:04:27,911\n点击启动 Codex 加加\n\n90\n00:04:32,151 --> 00:04:32,711\n打开\n\n91\n00:04:36,630 --> 00:04:36,870\n好\n\n92\n00:04:36,870 --> 00:04:39,511\n可以看到我们这已经打开成功打开 Codex 了\n\n93\n00:04:40,550 --> 00:04:43,110\n我们这个把这个点击删除就好了\n\n94\n00:04:43,591 --> 00:04:43,750\n好\n\n95\n00:04:43,750 --> 00:04:46,790\n可以看到我们这已经配置好了 V4\n\n96\n00:04:47,591 --> 00:04:50,310\n而且我们可以是自己选择 Flash Pro Pro 的\n\n97\n00:04:50,391 --> 00:04:55,190\n因为它通过你的 Base URL 会自动识别里面有什么模型\n\n98\n00:04:56,071 --> 00:04:58,071\n我们简简单进行一个测试一下\n\n99\n00:05:03,990 --> 00:05:04,151\n好\n\n100\n00:05:04,151 --> 00:05:07,350\n可以看到我们这里已经完全配置成功了\n\n101\n00:05:08,071 --> 00:05:14,471\n我们在整个过程中是没有使用任何魔法以及无需登录 Open A I 的官方账号的\n\n102\n00:05:15,911 --> 00:05:16,071\n好\n\n103\n00:05:16,071 --> 00:05:19,750\n现在我们开始一个 Windows 版的 Codex 安装\n\n104\n00:05:19,750 --> 00:05:20,310\n可以看到\n\n105\n00:05:21,031 --> 00:05:23,911\n我们现在这个 Codex 已经是已经卸载干净了\n\n106\n00:05:24,071 --> 00:05:25,430\n已经没有 Codex 这个程序\n\n107\n00:05:25,990 --> 00:05:27,511\n然后这两个安装包的话\n\n108\n00:05:27,511 --> 00:05:30,151\n可以在我简介区的网盘获取\n\n109\n00:05:30,630 --> 00:05:31,990\n我在网盘会分享给大家\n\n110\n00:05:33,670 --> 00:05:33,990\n好\n\n111\n00:05:34,630 --> 00:05:37,031\n我们先安装一下 Codex 本体\n\n112\n00:05:37,350 --> 00:05:38,071\n双击一下\n\n113\n00:05:57,149 --> 00:05:57,389\n好\n\n114\n00:05:57,389 --> 00:05:59,709\n可以看到我们这个是已经安装完成了\n\n115\n00:06:00,189 --> 00:06:03,548\n然后我们再安装我们的 Codex 加加\n\n116\n00:06:09,788 --> 00:06:10,269\n好\n\n117\n00:06:10,509 --> 00:06:13,149\n这样就已经是安装完成我们 Codex 加加了\n\n118\n00:06:15,228 --> 00:06:20,668\n搜索 Codex 加加启动管理器工具\n\n119\n00:06:20,749 --> 00:06:22,189\n我们启动这个\n\n120\n00:06:27,548 --> 00:06:30,108\n然后我们点击供应商配置\n\n121\n00:06:32,269 --> 00:06:33,548\n我们添加一下供应商\n\n122\n00:06:35,709 --> 00:06:37,309\n还是用我们的 Deepseek\n\n123\n00:06:40,269 --> 00:06:44,588\n因为 Deepseek 昨天刚宣布它的 V4 Pro 永久降价\n\n124\n00:06:45,709 --> 00:06:46,988\n我们这里选择纯 API\n\n125\n00:06:47,228 --> 00:06:52,668\n然后这里我们写一个 Deepseek V4 的 Flash 吧\n\n126\n00:06:56,988 --> 00:07:00,668\nUI 要就输我们 Deepseek 的 API 官方地址\n\n127\n00:07:03,149 --> 00:07:08,749\n密钥的话需要我们从 Deepseek 官方获取\n\n128\n00:07:10,108 --> 00:07:12,509\n然后我们再选择 Chat 模式\n\n129\n00:07:12,908 --> 00:07:13,788\n选择保存\n\n130\n00:07:15,069 --> 00:07:20,028\n然后我们这里使用我们刚刚配置好的一个供应商\n\n131\n00:07:20,988 --> 00:07:21,869\n我们测试一下\n\n132\n00:07:21,949 --> 00:07:22,269\n好\n\n133\n00:07:22,269 --> 00:07:23,468\n这里已经测试成功\n\n134\n00:07:25,949 --> 00:07:26,908\n回到概览\n\n135\n00:07:26,908 --> 00:07:28,509\n我们启动 Codex 加加\n\n136\n00:07:41,228 --> 00:07:42,028\n稍等一会儿\n\n137\n00:07:44,749 --> 00:07:48,829\n如果遇到这种等了很久还不行的情况的话\n\n138\n00:07:49,228 --> 00:07:51,788\n我们先关闭我们的 Codex 加加\n\n139\n00:07:52,348 --> 00:07:56,028\n然后再关闭我们这个管理器\n\n140\n00:07:56,509 --> 00:07:57,389\n再重启一下\n\n141\n00:08:02,108 --> 00:08:05,949\n我们点击重启 Codex\n\n142\n00:08:10,509 --> 00:08:10,509\n好\n\n143\n00:08:12,588 --> 00:08:13,788\n可以看到我们已经进来了\n\n144\n00:08:14,028 --> 00:08:17,629\n我们随便发一个请求\n\n145\n00:08:23,629 --> 00:08:23,709\n好\n\n146\n00:08:23,709 --> 00:08:25,949\n可以看到我们已经成功配置好了\n\n147\n00:08:26,108 --> 00:08:26,908\n在整个过程中\n\n148\n00:08:26,908 --> 00:08:28,588\n我们是没有使用任何魔法\n\n149\n00:08:29,149 --> 00:08:31,468\n以及无需登录 OpenAI 账号的\n\n150\n00:08:32,589 --> 00:08:36,509\n我们的 Windows 版和 Mac OS 版都提供了相应的教程\n\n151\n00:08:36,828 --> 00:08:40,908\n然后相应的安装包也会在评论区的简介给出来\n\n152\n00:08:41,389 --> 00:08:42,828\n大家自取就可以\n\n153\n00:08:43,308 --> 00:08:45,389\n我们这期视频先到这\n\n154\n00:08:45,389 --> 00:08:46,509\n下期视频再见\n\n"
]
},
{
"id": 216,
"type": "MelBandRoFormerModelLoader",
"pos": [
2367.10546875,
2955.939208984375
],
"size": [
256.2164001464844,
58
],
"flags": {},
"order": 9,
"mode": 4,
"inputs": [
{
"label": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
}
}
],
"outputs": [
{
"label": "model",
"name": "model",
"type": "MELROFORMERMODEL",
"links": [
254
]
}
],
"properties": {
"Node name for S&R": "MelBandRoFormerModelLoader",
"widget_ue_connectable": {}
},
"widgets_values": [
"MelBandRoFormer_comfy/MelBandRoformer_fp32.safetensors"
]
},
{
"id": 219,
"type": "MelBandRoFormerModelLoader",
"pos": [
2364.743408203125,
3643.93505859375
],
"size": [
256.2164001464844,
58
],
"flags": {},
"order": 10,
"mode": 4,
"inputs": [
{
"label": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
}
}
],
"outputs": [
{
"label": "model",
"name": "model",
"type": "MELROFORMERMODEL",
"links": [
257
]
}
],
"properties": {
"Node name for S&R": "MelBandRoFormerModelLoader",
"widget_ue_connectable": {}
},
"widgets_values": [
"MelBandRoFormer_comfy/MelBandRoformer_fp32.safetensors"
]
},
{
"id": 222,
"type": "SaveAudioMP3",
"pos": [
3016.73388671875,
3805.54052734375
],
"size": [
270,
136
],
"flags": {},
"order": 43,
"mode": 4,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 259
},
{
"label": "filename_prefix",
"name": "filename_prefix",
"type": "STRING",
"widget": {
"name": "filename_prefix"
}
},
{
"label": "quality",
"name": "quality",
"type": "COMBO",
"widget": {
"name": "quality"
}
},
{
"label": "audioUI",
"name": "audioUI",
"type": "AUDIO_UI",
"widget": {
"name": "audioUI"
}
}
],
"outputs": [],
"properties": {
"Node name for S&R": "SaveAudioMP3",
"widget_ue_connectable": {}
},
"widgets_values": [
"env",
"V0"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 218,
"type": "MelBandRoFormerSampler",
"pos": [
2684.156982421875,
3713.42529296875
],
"size": [
231.27206420898438,
46
],
"flags": {
"collapsed": false
},
"order": 30,
"mode": 4,
"inputs": [
{
"label": "model",
"name": "model",
"type": "MELROFORMERMODEL",
"link": 257
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 258
}
],
"outputs": [
{
"label": "vocals",
"name": "vocals",
"type": "AUDIO",
"links": [
260
]
},
{
"label": "instruments",
"name": "instruments",
"type": "AUDIO",
"links": [
259
]
}
],
"properties": {
"Node name for S&R": "MelBandRoFormerSampler",
"cnr_id": "ComfyUI-MelBandRoFormer",
"ver": "b40e263224778ec417114d91d8b3b39934e30de5",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.5.2"
},
"widget_ue_connectable": {}
},
"widgets_values": []
},
{
"id": 221,
"type": "SaveAudioMP3",
"pos": [
3008.08349609375,
3597.576171875
],
"size": [
270,
136
],
"flags": {},
"order": 42,
"mode": 4,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 260
},
{
"label": "filename_prefix",
"name": "filename_prefix",
"type": "STRING",
"widget": {
"name": "filename_prefix"
}
},
{
"label": "quality",
"name": "quality",
"type": "COMBO",
"widget": {
"name": "quality"
}
},
{
"label": "audioUI",
"name": "audioUI",
"type": "AUDIO_UI",
"widget": {
"name": "audioUI"
}
}
],
"outputs": [],
"properties": {
"Node name for S&R": "SaveAudioMP3",
"widget_ue_connectable": {}
},
"widgets_values": [
"vocals",
"V0"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 217,
"type": "LoadAudio",
"pos": [
2354.642822265625,
3759.3916015625
],
"size": [
281.5520324707031,
136
],
"flags": {},
"order": 11,
"mode": 4,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "COMBO",
"widget": {
"name": "audio"
}
},
{
"label": "audioUI",
"name": "audioUI",
"type": "AUDIO_UI",
"widget": {
"name": "audioUI"
}
},
{
"label": "upload",
"name": "upload",
"type": "AUDIOUPLOAD",
"widget": {
"name": "upload"
}
}
],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
258
]
}
],
"title": "输入原音频",
"properties": {
"Node name for S&R": "LoadAudio",
"cnr_id": "comfy-core",
"ver": "0.12.1",
"widget_ue_connectable": {
"upload": true,
"audio": true,
"audioUI": true
}
},
"widgets_values": [
"39edb0d466187fc60afc4506cf8a948516a0ccd7d23173e96b616c721d59c4dc.MP3",
null,
null
],
"color": "#323",
"bgcolor": "#535"
},
{
"id": 199,
"type": "LoadAudio",
"pos": [
2350.7373046875,
3090.96435546875
],
"size": [
281.5520324707031,
136
],
"flags": {},
"order": 12,
"mode": 4,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "COMBO",
"widget": {
"name": "audio"
}
},
{
"label": "audioUI",
"name": "audioUI",
"type": "AUDIO_UI",
"widget": {
"name": "audioUI"
}
},
{
"label": "upload",
"name": "upload",
"type": "AUDIOUPLOAD",
"widget": {
"name": "upload"
}
}
],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
256
]
}
],
"properties": {
"Node name for S&R": "LoadAudio",
"cnr_id": "comfy-core",
"ver": "0.12.1",
"widget_ue_connectable": {
"upload": true,
"audio": true,
"audioUI": true
}
},
"widgets_values": [
"2a18a079219a0ef3d78c9fa4c2b3f562f4278ab0a76e291118c51baf3532b862.mp3",
null,
null
]
},
{
"id": 45,
"type": "VoiceBridgeASRTranscribe",
"pos": [
2625.023681640625,
1668.61328125
],
"size": [
339.7463073730469,
196
],
"flags": {},
"order": 51,
"mode": 0,
"inputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"link": 208
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 89
},
{
"label": "language",
"name": "language",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "language"
}
},
{
"label": "context",
"name": "context",
"shape": 7,
"type": "STRING",
"widget": {
"name": "context"
}
},
{
"label": "return_timestamps",
"name": "return_timestamps",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "return_timestamps"
}
},
{
"label": "model",
"name": "model",
"type": "QWEN3_ASR_MODEL"
}
],
"outputs": [
{
"label": "forced_aligns",
"name": "forced_aligns",
"type": "LIST",
"links": []
},
{
"label": "text",
"name": "text",
"type": "STRING",
"links": [
163
]
},
{
"label": "language",
"name": "language",
"type": "STRING"
},
{
"label": "timestamps",
"name": "timestamps",
"type": "STRING"
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRTranscribe",
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a",
"widget_ue_connectable": {
"context": true,
"language": true,
"return_timestamps": true
}
},
"widgets_values": [
"auto",
"",
false
]
},
{
"id": 177,
"type": "VoiceBridgeSRTSplitter",
"pos": [
3585.71923828125,
1765.0225830078125
],
"size": [
266.1524658203125,
281.7366943359375
],
"flags": {},
"order": 33,
"mode": 0,
"inputs": [
{
"label": "srt_string",
"name": "srt_string",
"type": "STRING",
"widget": {
"name": "srt_string"
},
"link": 292
}
],
"outputs": [
{
"label": "texts",
"name": "texts",
"shape": 6,
"type": "STRING",
"links": [
246
]
},
{
"label": "srt_items",
"name": "srt_items",
"type": "VB_SRT_ITEMS",
"links": [
219
]
},
{
"label": "count",
"name": "count",
"type": "INT"
}
],
"properties": {
"Node name for S&R": "VoiceBridgeSRTSplitter",
"cnr_id": "comfyui_voicebridge",
"ver": "5149c68df1d156794999bd77ff6a86fcab0314ed",
"widget_ue_connectable": {
"srt_string": true
}
},
"widgets_values": [
"1\n00:00:02,080 --> 00:00:03,200\n全民制作人们 大家好\n\n2\n00:00:03,439 --> 00:00:06,160\n我是练习时长两年半的个人练习生蔡徐坤\n\n3\n00:00:06,480 --> 00:00:09,359\n喜欢唱、跳、rap、篮球、music\n\n"
]
},
{
"id": 253,
"type": "VoiceBridgeASRTranscribe",
"pos": [
1624.9632568359375,
2002.8311767578125
],
"size": [
339.7463073730469,
196
],
"flags": {},
"order": 36,
"mode": 4,
"inputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"link": 312
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 302
},
{
"label": "model",
"name": "model",
"type": "QWEN3_ASR_MODEL",
"link": null
}
],
"outputs": [
{
"label": "forced_aligns",
"name": "forced_aligns",
"type": "LIST",
"links": []
},
{
"label": "text",
"name": "text",
"type": "STRING",
"links": [
304,
305
]
},
{
"label": "language",
"name": "language",
"type": "STRING"
},
{
"label": "timestamps",
"name": "timestamps",
"type": "STRING"
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRTranscribe",
"widget_ue_connectable": {
"context": true,
"language": true,
"return_timestamps": true
},
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a"
},
"widgets_values": [
"auto",
"",
false
]
},
{
"id": 254,
"type": "SetNode",
"pos": [
1992.2423095703125,
1778.9376220703125
],
"size": [
210,
58
],
"flags": {},
"order": 32,
"mode": 4,
"inputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"link": 303
}
],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO"
}
],
"title": "Set_Custom audio",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Custom audio",
"widget_ue_connectable": {}
},
"widgets_values": [
"Custom audio"
]
},
{
"id": 255,
"type": "SetNode",
"pos": [
1995.6175537109375,
1897.886474609375
],
"size": [
210,
58
],
"flags": {},
"order": 46,
"mode": 4,
"inputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"link": 304
}
],
"outputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING"
}
],
"title": "Set_Custom text",
"properties": {
"Node name for S&R": "SetNode",
"aux_id": "SetNode",
"previousName": "Custom text",
"widget_ue_connectable": {}
},
"widgets_values": [
"Custom text"
]
},
{
"id": 256,
"type": "easy showAnything",
"pos": [
1982.5074462890625,
2029.7125244140625
],
"size": [
234.05416870117188,
160.82620239257812
],
"flags": {},
"order": 47,
"mode": 4,
"inputs": [
{
"label": "anything",
"name": "anything",
"shape": 7,
"type": "*",
"link": 305
}
],
"outputs": [
{
"label": "output",
"name": "output",
"type": "*"
}
],
"properties": {
"Node name for S&R": "easy showAnything",
"widget_ue_connectable": {}
},
"widgets_values": [
"Hello everyone. I'm Sam Fading. Today, I'm showing an AI image generation tool with you."
]
},
{
"id": 257,
"type": "Note",
"pos": [
1280.0838623046875,
1770.927001953125
],
"size": [
260.1112976074219,
232.46372985839844
],
"flags": {},
"order": 13,
"mode": 4,
"inputs": [],
"outputs": [],
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": [
"在这里你可以加载一段你本人使用目标语言发音的纯人声音频,这样翻译出来的音频会更接近你本人的音色。默认使用原音频作为参考音频。如需使用自定义音频,加载自定义音频并启用“Custom audio ASR”模块后运行工作流即可\n\nHere you can load a clear audio clip of yourself speaking in the target language. This will help the translated audio sound more like your own voice.By default, the original audio is used as the reference audio. If you want to use a custom audio, load the custom audio and enable the \"Custom audio ASR\" module before running the workflow."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 258,
"type": "Note",
"pos": [
1873.6168212890625,
1583.871337890625
],
"size": [
350.62066650390625,
88
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "节点地址",
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": [
"https://github.com/YanTianlong-01/comfyui_voicebridge"
],
"color": "#223",
"bgcolor": "#335",
"shape": 4
},
{
"id": 259,
"type": "LoadAudio",
"pos": [
1562.6785888671875,
1781.4361572265625
],
"size": [
270,
136
],
"flags": {},
"order": 15,
"mode": 4,
"inputs": [],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
302,
303
]
}
],
"title": "输入参考音频",
"properties": {
"Node name for S&R": "LoadAudio",
"widget_ue_connectable": {}
},
"widgets_values": [
"dd52a5d800491ba8577a321130f2e8f6284720985448c08bfd1e291525bfcfef.mp3",
null,
null
],
"color": "#232",
"bgcolor": "#353"
},
{
"id": 147,
"type": "GetNode",
"pos": [
3336.365234375,
1838.817626953125
],
"size": [
210,
60
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
292
]
}
],
"title": "Get_Translated SRT",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Translated SRT"
]
},
{
"id": 249,
"type": "GetNode",
"pos": [
3319.0615234375,
2119.168701171875
],
"size": [
219.67147827148438,
58
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
306
]
}
],
"title": "Get_Original reference audio",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Original reference audio"
]
},
{
"id": 262,
"type": "GetNode",
"pos": [
3333.01025390625,
2236.693359375
],
"size": [
210,
58
],
"flags": {},
"order": 18,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
308
]
}
],
"title": "Get_Custom audio",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Custom audio"
]
},
{
"id": 264,
"type": "Any Switch (rgthree)",
"pos": [
3948.931396484375,
2242.158447265625
],
"size": [
166.72030639648438,
106
],
"flags": {},
"order": 35,
"mode": 0,
"inputs": [
{
"dir": 3,
"label": "any_01",
"name": "any_01",
"type": "STRING",
"link": 309
},
{
"dir": 3,
"label": "any_02",
"name": "any_02",
"type": "STRING",
"link": 311
},
{
"dir": 3,
"label": "any_03",
"name": "any_03",
"type": "STRING",
"link": null
},
{
"dir": 3,
"label": "any_04",
"name": "any_04",
"type": "STRING",
"link": null
},
{
"dir": 3,
"name": "any_05",
"type": "STRING",
"link": null
}
],
"outputs": [
{
"dir": 4,
"label": "STRING",
"name": "*",
"shape": 3,
"type": "STRING",
"links": [
310
]
}
],
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": []
},
{
"id": 248,
"type": "GetNode",
"pos": [
3614.5537109375,
2267.921630859375
],
"size": [
219.67147827148438,
58
],
"flags": {},
"order": 19,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
309
]
}
],
"title": "Get_Reference text",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Reference text"
]
},
{
"id": 263,
"type": "GetNode",
"pos": [
3625.853759765625,
2368.80224609375
],
"size": [
210,
58
],
"flags": {},
"order": 20,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
311
]
}
],
"title": "Get_Custom text",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Custom text"
]
},
{
"id": 252,
"type": "VoiceBridgeASRLoader",
"pos": [
1284.2056884765625,
2059.259033203125
],
"size": [
293.85516357421875,
155.7703857421875
],
"flags": {},
"order": 21,
"mode": 4,
"inputs": [],
"outputs": [
{
"label": "model_key",
"name": "model_key",
"type": "MODEL_KEY",
"links": [
312
]
}
],
"properties": {
"Node name for S&R": "VoiceBridgeASRLoader",
"widget_ue_connectable": {
"forced_aligner": true,
"max_new_tokens": true,
"precision": true,
"attention": true
},
"cnr_id": "comfyui_voicebridge",
"ver": "ddefcc0082ab9591f9b613f0de565f25f85d8f2a"
},
"widgets_values": [
"Qwen/Qwen3-ASR-1.7B",
"bf16",
"flash_attention_2",
1024,
"Qwen/Qwen3-ForcedAligner-0.6B"
]
},
{
"id": 260,
"type": "Fast Groups Bypasser (rgthree)",
"pos": [
1270.8333740234375,
1606.4197998046875
],
"size": [
370.3751220703125,
63.666927337646484
],
"flags": {},
"order": 22,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "OPT_CONNECTION",
"name": "OPT_CONNECTION",
"type": "*"
}
],
"title": "是否使用单独的参考音频",
"properties": {
"matchColors": "",
"matchTitle": "可选",
"showNav": true,
"sort": "position",
"customSortAlphabet": "",
"toggleRestriction": "default",
"widget_ue_connectable": {}
},
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 153,
"type": "Note",
"pos": [
2511.468994140625,
1331.1826171875
],
"size": [
231.91683959960938,
91.09986114501953
],
"flags": {},
"order": 23,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": [
"目标语言就是你想要翻译成的语言,请从下面拷贝:\nArabic, Burmese, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Tagalog, Thai, Turkish, Vietnamese"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 99,
"type": "MelBandRoFormerSampler",
"pos": [
2569.349609375,
1162.954833984375
],
"size": [
231.27206420898438,
46
],
"flags": {
"collapsed": false
},
"order": 37,
"mode": 0,
"inputs": [
{
"label": "model",
"name": "model",
"type": "MELROFORMERMODEL",
"link": 137
},
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 205
}
],
"outputs": [
{
"label": "vocals",
"name": "vocals",
"type": "AUDIO",
"links": [
159
]
},
{
"label": "instruments",
"name": "instruments",
"type": "AUDIO",
"links": [
199
]
}
],
"properties": {
"Node name for S&R": "MelBandRoFormerSampler",
"cnr_id": "ComfyUI-MelBandRoFormer",
"ver": "b40e263224778ec417114d91d8b3b39934e30de5",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.5.2"
},
"widget_ue_connectable": {}
},
"widgets_values": []
},
{
"id": 16,
"type": "LoadAudio",
"pos": [
2259.259521484375,
1146.6513671875
],
"size": [
281.5520324707031,
136
],
"flags": {},
"order": 24,
"mode": 0,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "COMBO",
"widget": {
"name": "audio"
}
},
{
"label": "audioUI",
"name": "audioUI",
"type": "AUDIO_UI",
"widget": {
"name": "audioUI"
}
},
{
"label": "upload",
"name": "upload",
"type": "AUDIOUPLOAD",
"widget": {
"name": "upload"
}
}
],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
205
]
}
],
"title": "输入原音频",
"properties": {
"Node name for S&R": "LoadAudio",
"cnr_id": "comfy-core",
"ver": "0.12.1",
"widget_ue_connectable": {
"upload": true,
"audio": true,
"audioUI": true
}
},
"widgets_values": [
"fcecb7fd3827851a4fb22c52886610aed0a62e5fe32ea46f3b1291ff3dd236ab.mp3",
null,
null
],
"color": "#232",
"bgcolor": "#353"
},
{
"id": 261,
"type": "Any Switch (rgthree)",
"pos": [
3965.07763671875,
2040.2728271484375
],
"size": [
166.72030639648438,
106
],
"flags": {},
"order": 34,
"mode": 0,
"inputs": [
{
"dir": 3,
"label": "any_01",
"name": "any_01",
"type": "AUDIO",
"link": 306
},
{
"dir": 3,
"label": "any_02",
"name": "any_02",
"type": "AUDIO",
"link": 308
},
{
"dir": 3,
"label": "any_03",
"name": "any_03",
"type": "AUDIO",
"link": null
},
{
"dir": 3,
"label": "any_04",
"name": "any_04",
"type": "AUDIO",
"link": null
},
{
"dir": 3,
"name": "any_05",
"type": "AUDIO",
"link": null
}
],
"outputs": [
{
"dir": 4,
"label": "AUDIO",
"name": "*",
"shape": 3,
"type": "AUDIO",
"links": [
307
]
}
],
"properties": {
"widget_ue_connectable": {}
},
"widgets_values": []
},
{
"id": 207,
"type": "RunningHub_VoxCPM_LoadModel",
"pos": [
3930.92919921875,
1785.65771484375
],
"size": [
253.14022827148438,
106
],
"flags": {},
"order": 25,
"mode": 0,
"inputs": [
{
"label": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
}
},
{
"label": "optimize",
"name": "optimize",
"type": "BOOLEAN",
"widget": {
"name": "optimize"
}
},
{
"label": "lora_name",
"name": "lora_name",
"shape": 7,
"type": "COMBO",
"widget": {
"name": "lora_name"
}
}
],
"outputs": [
{
"label": "model",
"name": "model",
"type": "VOXCPM_MODEL",
"links": [
245
]
}
],
"properties": {
"Node name for S&R": "RunningHub_VoxCPM_LoadModel",
"widget_ue_connectable": {}
},
"widgets_values": [
"VoxCPM2",
false,
"None"
],
"color": "#233",
"bgcolor": "#355"
},
{
"id": 110,
"type": "easy string",
"pos": [
2278.14697265625,
1337.082275390625
],
"size": [
210,
58
],
"flags": {},
"order": 26,
"mode": 0,
"inputs": [
{
"label": "value",
"name": "value",
"type": "STRING",
"widget": {
"name": "value"
}
}
],
"outputs": [
{
"label": "string",
"name": "string",
"type": "STRING",
"links": [
151
]
}
],
"title": "输入目标语言",
"properties": {
"Node name for S&R": "easy string",
"widget_ue_connectable": {}
},
"widgets_values": [
"English"
],
"color": "#232",
"bgcolor": "#353"
},
{
"id": 116,
"type": "GetNode",
"pos": [
2288.33984375,
1647.5472412109375
],
"size": [
225.12655639648438,
60
],
"flags": {},
"order": 27,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
160,
161
]
}
],
"title": "Get_Separated human voices",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Separated human voices"
]
},
{
"id": 46,
"type": "TrimAudioDuration",
"pos": [
2289.86181640625,
1769.0185546875
],
"size": [
210,
82
],
"flags": {},
"order": 39,
"mode": 0,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 160
},
{
"label": "start_index",
"name": "start_index",
"type": "FLOAT",
"widget": {
"name": "start_index"
}
},
{
"label": "duration",
"name": "duration",
"type": "FLOAT",
"widget": {
"name": "duration"
}
}
],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
89,
162
]
}
],
"properties": {
"Node name for S&R": "TrimAudioDuration",
"cnr_id": "comfy-core",
"ver": "0.12.1",
"widget_ue_connectable": {
"duration": true,
"start_index": true
}
},
"widgets_values": [
0,
10.000000000000002
]
},
{
"id": 206,
"type": "RunningHub_VoxCPM_Generate",
"pos": [
4257.484375,
1793.946044921875
],
"size": [
408.29345703125,
567.8054809570312
],
"flags": {},
"order": 45,
"mode": 0,
"inputs": [
{
"label": "model",
"name": "model",
"type": "VOXCPM_MODEL",
"link": 245
},
{
"label": "reference_audio",
"name": "reference_audio",
"shape": 7,
"type": "AUDIO",
"link": 307
},
{
"label": "control_instruction",
"name": "control_instruction",
"type": "STRING",
"widget": {
"name": "control_instruction"
}
},
{
"label": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 246
},
{
"label": "cfg_value",
"name": "cfg_value",
"type": "FLOAT",
"widget": {
"name": "cfg_value"
}
},
{
"label": "inference_steps",
"name": "inference_steps",
"type": "INT",
"widget": {
"name": "inference_steps"
}
},
{
"label": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
}
},
{
"label": "ultimate_clone",
"name": "ultimate_clone",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "ultimate_clone"
}
},
{
"label": "reference_audio_text",
"name": "reference_audio_text",
"shape": 7,
"type": "STRING",
"widget": {
"name": "reference_audio_text"
},
"link": 310
},
{
"label": "normalize_text",
"name": "normalize_text",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "normalize_text"
}
},
{
"label": "denoise_reference",
"name": "denoise_reference",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "denoise_reference"
}
},
{
"label": "max_len",
"name": "max_len",
"shape": 7,
"type": "INT",
"widget": {
"name": "max_len"
}
},
{
"label": "retry_badcase",
"name": "retry_badcase",
"shape": 7,
"type": "BOOLEAN",
"widget": {
"name": "retry_badcase"
}
}
],
"outputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"links": [
315
]
}
],
"properties": {
"Node name for S&R": "RunningHub_VoxCPM_Generate",
"widget_ue_connectable": {}
},
"widgets_values": [
"",
"Hello, this is a test.",
2,
10,
220751697769047,
"randomize",
true,
"This is a moose, right?\nOh, that's how it works, so it depend on the peak.",
false,
false,
4096,
true
],
"color": "#233",
"bgcolor": "#355"
},
{
"id": 176,
"type": "VoiceBridgeAudioListMergerBySRT",
"pos": [
4734.8857421875,
1678.13232421875
],
"size": [
316.6376647949219,
129.57545471191406
],
"flags": {},
"order": 62,
"mode": 0,
"inputs": [
{
"label": "srt_items",
"name": "srt_items",
"type": "VB_SRT_ITEMS",
"link": 219
},
{
"label": "audios",
"name": "audios",
"type": "AUDIO",
"link": 316
},
{
"label": "tempo_limit",
"name": "tempo_limit",
"shape": 7,
"type": "FLOAT",
"widget": {
"name": "tempo_limit"
}
},
{
"label": "mini_gap_ms",
"name": "mini_gap_ms",
"shape": 7,
"type": "INT",
"widget": {
"name": "mini_gap_ms"
}
}
],
"outputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"links": [
296
]
},
{
"label": "adjusted_srt",
"name": "adjusted_srt",
"type": "STRING",
"links": [
223
]
}
],
"properties": {
"Node name for S&R": "VoiceBridgeAudioListMergerBySRT",
"cnr_id": "comfyui_voicebridge",
"ver": "5149c68df1d156794999bd77ff6a86fcab0314ed",
"widget_ue_connectable": {
"tempo_limit": true,
"mini_gap_ms": true
}
},
"widgets_values": [
2,
10
]
},
{
"id": 214,
"type": "SaveSRTFromString",
"pos": [
5480.3583984375,
1923.338623046875
],
"size": [
270,
82
],
"flags": {},
"order": 66,
"mode": 0,
"inputs": [
{
"label": "srt_string",
"name": "srt_string",
"type": "STRING",
"widget": {
"name": "srt_string"
},
"link": 253
},
{
"label": "filename_prefix",
"name": "filename_prefix",
"shape": 7,
"type": "STRING",
"widget": {
"name": "filename_prefix"
}
}
],
"outputs": [
{
"label": "save_path",
"name": "save_path",
"type": "STRING"
}
],
"properties": {
"Node name for S&R": "SaveSRTFromString",
"widget_ue_connectable": {}
},
"widgets_values": [
"",
"VoiceBridge/subtitle"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 179,
"type": "easy showAnything",
"pos": [
5090.2705078125,
1930.040283203125
],
"size": [
364.845947265625,
379.28558349609375
],
"flags": {},
"order": 64,
"mode": 0,
"inputs": [
{
"label": "anything",
"name": "anything",
"shape": 7,
"type": "*",
"link": 223
}
],
"outputs": [
{
"label": "output",
"name": "output",
"type": "*",
"links": [
253
]
}
],
"properties": {
"Node name for S&R": "easy showAnything",
"cnr_id": "comfyui-easy-use",
"ver": "1.3.6",
"widget_ue_connectable": {}
},
"widgets_values": [
"1\n00:00:00,000 --> 00:00:03,540\nI bet you've seen a comment like this under all kinds of content.\n\n2\n00:00:03,550 --> 00:00:04,681\nA few months ago,\n\n3\n00:00:04,960 --> 00:00:06,851\neveryone used it as a joke.\n\n4\n00:00:06,861 --> 00:00:07,835\nIt was a meme.\n\n5\n00:00:07,845 --> 00:00:08,400\nRight?\n\n6\n00:00:08,410 --> 00:00:09,683\nYou see something absurd.\n\n7\n00:00:09,693 --> 00:00:10,536\nYou'd say,\n\n8\n00:00:10,546 --> 00:00:10,996\n\"Ah,\n\n9\n00:00:11,006 --> 00:00:13,018\nmust be AI, or AI is too good.\n\n10\n00:00:13,028 --> 00:00:13,837\nBro.\"\n\n11\n00:00:13,847 --> 00:00:14,700\nBut the interesting thing is,\n\n12\n00:00:14,710 --> 00:00:15,946\njust a few months later,\n\n13\n00:00:15,956 --> 00:00:20,245\nnow the emotion behind \"Is this AI?\" has changed.\n\n14\n00:00:20,255 --> 00:00:23,795\nBecause AI has gotten even stronger.\n"
]
},
{
"id": 251,
"type": "MergeAudioMW",
"pos": [
5330.80029296875,
1707.669921875
],
"size": [
164.431640625,
46
],
"flags": {},
"order": 63,
"mode": 0,
"inputs": [
{
"label": "audio_1",
"name": "audio_1",
"type": "AUDIO",
"link": 296
},
{
"label": "audio_2",
"name": "audio_2",
"type": "AUDIO",
"link": 295
}
],
"outputs": [
{
"label": "merged_audio",
"name": "merged_audio",
"type": "AUDIO",
"links": [
297
]
}
],
"properties": {
"Node name for S&R": "MergeAudioMW",
"widget_ue_connectable": {}
},
"widgets_values": []
},
{
"id": 250,
"type": "GetNode",
"pos": [
5100.14599609375,
1779.1236572265625
],
"size": [
210,
58
],
"flags": {},
"order": 28,
"mode": 0,
"inputs": [],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
295
]
}
],
"title": "Get_Ambient sound",
"properties": {
"Node name for S&R": "GetNode",
"aux_id": "GetNode",
"widget_ue_connectable": {}
},
"widgets_values": [
"Ambient sound"
]
},
{
"id": 268,
"type": "TrimAudioDuration",
"pos": [
4716.50341796875,
1887.7354736328125
],
"size": [
210,
82
],
"flags": {},
"order": 57,
"mode": 0,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 315
}
],
"outputs": [
{
"label": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
316
]
}
],
"properties": {
"Node name for S&R": "TrimAudioDuration",
"widget_ue_connectable": {
"duration": true,
"start_index": true
},
"cnr_id": "comfy-core",
"ver": "0.12.1"
},
"widgets_values": [
0.30000000000000004,
100.00000000000001
]
},
{
"id": 180,
"type": "SaveAudioMP3",
"pos": [
5515.87353515625,
1697.279052734375
],
"size": [
270,
136
],
"flags": {},
"order": 65,
"mode": 0,
"inputs": [
{
"label": "audio",
"name": "audio",
"type": "AUDIO",
"link": 297
},
{
"label": "filename_prefix",
"name": "filename_prefix",
"type": "STRING",
"widget": {
"name": "filename_prefix"
}
},
{
"label": "quality",
"name": "quality",
"type": "COMBO",
"widget": {
"name": "quality"
}
},
{
"label": "audioUI",
"name": "audioUI",
"type": "AUDIO_UI",
"widget": {
"name": "audioUI"
}
}
],
"outputs": [],
"properties": {
"Node name for S&R": "SaveAudioMP3",
"cnr_id": "comfy-core",
"ver": "0.12.1",
"widget_ue_connectable": {
"filename_prefix": true,
"audioUI": true,
"quality": true
}
},
"widgets_values": [
"audio/ComfyUI",
"V0"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 105,
"type": "RH_LLMAPI_NODE",
"pos": [
4226.4248046875,
973.7415771484375
],
"size": [
400,
396
],
"flags": {},
"order": 50,
"mode": 0,
"inputs": [
{
"label": "ref_image",
"name": "ref_image",
"shape": 7,
"type": "IMAGE"
},
{
"label": "video",
"name": "video",
"shape": 7,
"type": "VIDEO"
},
{
"label": "ref_image1",
"name": "ref_image1",
"shape": 7,
"type": "IMAGE"
},
{
"label": "ref_image2",
"name": "ref_image2",
"shape": 7,
"type": "IMAGE"
},
{
"label": "ref_image3",
"name": "ref_image3",
"shape": 7,
"type": "IMAGE"
},
{
"label": "api_baseurl",
"name": "api_baseurl",
"type": "STRING",
"widget": {
"name": "api_baseurl"
}
},
{
"label": "api_key",
"name": "api_key",
"type": "STRING",
"widget": {
"name": "api_key"
}
},
{
"label": "model",
"name": "model",
"type": "STRING",
"widget": {
"name": "model"
}
},
{
"label": "role",
"name": "role",
"type": "STRING",
"widget": {
"name": "role"
},
"link": 150
},
{
"label": "prompt",
"name": "prompt",
"type": "STRING",
"widget": {
"name": "prompt"
},
"link": 146
},
{
"label": "temperature",
"name": "temperature",
"type": "FLOAT",
"widget": {
"name": "temperature"
}
},
{
"label": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
}
}
],
"outputs": [
{
"label": "describe",
"name": "describe",
"type": "STRING",
"links": [
147,
172
]
}
],
"properties": {
"Node name for S&R": "RH_LLMAPI_NODE",
"widget_ue_connectable": {}
},
"widgets_values": [
"https://api.deepseek.com",
"",
"deepseek-v4-flash",
"",
"Hello",
0.5,
1761935326,
"randomize"
]
}
],
"links": [
[
89,
46,
0,
45,
1,
"AUDIO"
],
[
104,
36,
0,
61,
0,
"*"
],
[
137,
96,
0,
99,
0,
"MELROFORMERMODEL"
],
[
146,
36,
0,
105,
9,
"STRING"
],
[
147,
105,
0,
107,
0,
"*"
],
[
149,
108,
0,
109,
0,
"STRING"
],
[
150,
109,
0,
105,
8,
"STRING"
],
[
151,
110,
0,
109,
2,
"STRING"
],
[
159,
99,
0,
115,
0,
"*"
],
[
160,
116,
0,
46,
0,
"AUDIO"
],
[
161,
116,
0,
33,
1,
"AUDIO"
],
[
162,
46,
0,
117,
0,
"*"
],
[
163,
45,
1,
118,
0,
"*"
],
[
166,
33,
0,
121,
0,
"*"
],
[
167,
33,
1,
122,
0,
"*"
],
[
168,
33,
2,
123,
0,
"*"
],
[
169,
124,
0,
36,
0,
"LIST"
],
[
170,
125,
0,
36,
1,
"STRING"
],
[
171,
126,
0,
36,
2,
"STRING"
],
[
172,
105,
0,
127,
0,
"*"
],
[
199,
99,
1,
164,
0,
"*"
],
[
205,
16,
0,
99,
1,
"AUDIO"
],
[
208,
31,
0,
45,
0,
"MODEL_KEY"
],
[
209,
31,
0,
33,
0,
"MODEL_KEY"
],
[
219,
177,
1,
176,
0,
"VB_SRT_ITEMS"
],
[
223,
176,
1,
179,
0,
"*"
],
[
239,
202,
0,
200,
0,
"LIST"
],
[
240,
202,
1,
200,
1,
"STRING"
],
[
241,
202,
2,
200,
2,
"STRING"
],
[
242,
200,
0,
201,
0,
"*"
],
[
243,
198,
0,
202,
0,
"MODEL_KEY"
],
[
245,
207,
0,
206,
0,
"VOXCPM_MODEL"
],
[
246,
177,
0,
206,
3,
"STRING"
],
[
253,
179,
0,
214,
0,
"STRING"
],
[
254,
216,
0,
215,
0,
"MELROFORMERMODEL"
],
[
255,
215,
0,
202,
1,
"AUDIO"
],
[
256,
199,
0,
215,
1,
"AUDIO"
],
[
257,
219,
0,
218,
0,
"MELROFORMERMODEL"
],
[
258,
217,
0,
218,
1,
"AUDIO"
],
[
259,
218,
1,
222,
0,
"AUDIO"
],
[
260,
218,
0,
221,
0,
"AUDIO"
],
[
292,
147,
0,
177,
0,
"STRING"
],
[
295,
250,
0,
251,
1,
"AUDIO"
],
[
296,
176,
0,
251,
0,
"AUDIO"
],
[
297,
251,
0,
180,
0,
"AUDIO"
],
[
302,
259,
0,
253,
1,
"AUDIO"
],
[
303,
259,
0,
254,
0,
"*"
],
[
304,
253,
1,
255,
0,
"*"
],
[
305,
253,
1,
256,
0,
"*"
],
[
306,
249,
0,
261,
0,
"*"
],
[
307,
261,
0,
206,
1,
"AUDIO"
],
[
308,
262,
0,
261,
1,
"AUDIO"
],
[
309,
248,
0,
264,
0,
"*"
],
[
310,
264,
0,
206,
8,
"STRING"
],
[
311,
263,
0,
264,
1,
"STRING"
],
[
312,
252,
0,
253,
0,
"MODEL_KEY"
],
[
315,
206,
0,
268,
0,
"AUDIO"
],
[
316,
268,
0,
176,
1,
"AUDIO"
]
],
"floatingLinks": [
{
"id": 2,
"origin_id": 177,
"origin_slot": 0,
"target_id": -1,
"target_slot": -1,
"type": "STRING",
"parentId": 2
}
],
"groups": [
{
"id": 4,
"title": "Bilibili/Youtube:SevnFading",
"bounding": [
2136.488037109375,
-41.368934631347656,
3076.588623046875,
327.84368896484375
],
"color": "#3f789e",
"font_size": 240,
"flags": {}
},
{
"id": 5,
"title": "在使用此工作流前,请先点关注以下频道,谢谢",
"bounding": [
1177.0711669921875,
-555.101806640625,
5060.861328125,
334.6159973144531
],
"color": "#8AA",
"font_size": 240,
"flags": {}
},
{
"id": 6,
"title": "VoiceGate:跨语言视频智能配音引擎",
"bounding": [
1557.17529296875,
433.12554931640625,
4059.458740234375,
332.25274658203125
],
"color": "#88A",
"font_size": 240,
"flags": {}
},
{
"id": 8,
"title": "1 VoiceBridge ASR",
"bounding": [
2275.541015625,
1573.9482421875,
976.2326049804688,
682.24169921875
],
"color": "#b06634",
"font_size": 24,
"flags": {}
},
{
"id": 9,
"title": "2 VoiceBridge SRT Translate",
"bounding": [
3140.58349609375,
900.141357421875,
1882.4110107421875,
600.83251953125
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 11,
"title": "输入:Human voice separation",
"bounding": [
2244.635498046875,
899.3278198242188,
833.7108764648438,
603.8146362304688
],
"color": "#A88",
"font_size": 24,
"flags": {}
},
{
"id": 14,
"title": "3 SRT To Audio by VoxCPM TTS",
"bounding": [
3312.4443359375,
1550.8043212890625,
2494.289794921875,
908.720703125
],
"color": "#88A",
"font_size": 24,
"flags": {}
},
{
"id": 15,
"title": "VoxCPM TTS",
"bounding": [
3917.070068359375,
1707.8994140625,
764.7679443359375,
733.7567749023438
],
"color": "#88A",
"font_size": 24,
"flags": {}
},
{
"id": 20,
"title": "3-音频转字幕",
"bounding": [
2321.3662109375,
2821.237548828125,
2161.23583984375,
473.541015625
],
"color": "#b06634",
"font_size": 60,
"flags": {}
},
{
"id": 24,
"title": "4-人声背景声分离",
"bounding": [
2326.268310546875,
3393.2724609375,
1043.11376953125,
610.8731689453125
],
"color": "#3f789e",
"font_size": 60,
"flags": {}
},
{
"id": 27,
"title": "输入(可选):Custom audio ASR",
"bounding": [
1268.6402587890625,
1688.833984375,
967.5845947265625,
534.5038452148438
],
"color": "#A88",
"font_size": 24,
"flags": {}
}
],
"config": {},
"extra": {
"links_added_by_ue": [],
"VHS_KeepIntermediate": true,
"ue_links": [],
"VHS_MetadataImage": true,
"0246.VERSION": [
0,
0,
4
],
"workflowRendererVersion": "LG",
"VHS_latentpreviewrate": 0,
"reroutes": [
{
"id": 1,
"pos": [
3918.572021484375,
1685.84912109375
],
"linkIds": [
219
]
},
{
"id": 2,
"pos": [
3892.281494140625,
1942.5203857421875
],
"linkIds": [
246
],
"floating": {
"slotType": "output"
}
}
],
"frontendVersion": "1.23.0",
"VHS_latentpreview": false,
"ds": {
"scale": 0.724729500000006,
"offset": [
-2944.952705412889,
-704.6755215932656
]
},
"linkExtensions": [
{
"id": 219,
"parentId": 1
},
{
"id": 246,
"parentId": 2
}
]
},
"version": 0.4
}