workflows/voicegate_api.json

{
  "16": {
    "inputs": {
      "audio": "fcecb7fd3827851a4fb22c52886610aed0a62e5fe32ea46f3b1291ff3dd236ab.mp3",
      "audioUI": ""
    },
    "class_type": "LoadAudio",
    "_meta": {
      "title": "输入原音频"
    }
  },
  "31": {
    "inputs": {
      "repo_id": "Qwen/Qwen3-ASR-1.7B",
      "precision": "bf16",
      "attention": "flash_attention_2",
      "max_new_tokens": 1024,
      "forced_aligner": "Qwen/Qwen3-ForcedAligner-0.6B"
    },
    "class_type": "VoiceBridgeASRLoader",
    "_meta": {
      "title": "VoiceBridge ASR Loader"
    }
  },
  "33": {
    "inputs": {
      "language": "auto",
      "context": "",
      "return_timestamps": true,
      "model_key": [
        "31",
        0
      ],
      "audio": [
        "99",
        0
      ]
    },
    "class_type": "VoiceBridgeASRTranscribe",
    "_meta": {
      "title": "VoiceBridge ASR Transcribe"
    }
  },
  "36": {
    "inputs": {
      "text": [
        "33",
        1
      ],
      "language": [
        "33",
        2
      ],
      "save_srt": true,
      "filename_prefix": "VoiceBridge/subtitle",
      "forced_aligns": [
        "33",
        0
      ]
    },
    "class_type": "GenerateSRT",
    "_meta": {
      "title": "Generate SRT"
    }
  },
  "45": {
    "inputs": {
      "language": "auto",
      "context": "",
      "return_timestamps": false,
      "model_key": [
        "31",
        0
      ],
      "audio": [
        "46",
        0
      ]
    },
    "class_type": "VoiceBridgeASRTranscribe",
    "_meta": {
      "title": "VoiceBridge ASR Transcribe"
    }
  },
  "46": {
    "inputs": {
      "start_index": 0,
      "duration": 10.000000000000002,
      "audio": [
        "99",
        0
      ]
    },
    "class_type": "TrimAudioDuration",
    "_meta": {
      "title": "Trim Audio Duration"
    }
  },
  "61": {
    "inputs": {
      "text": "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",
      "anything": [
        "36",
        0
      ]
    },
    "class_type": "easy showAnything",
    "_meta": {
      "title": "Show Any"
    }
  },
  "96": {
    "inputs": {
      "model_name": "MelBandRoFormer_comfy/MelBandRoformer_fp32.safetensors"
    },
    "class_type": "MelBandRoFormerModelLoader",
    "_meta": {
      "title": "Mel-Band RoFormer Model Loader"
    }
  },
  "99": {
    "inputs": {
      "model": [
        "96",
        0
      ],
      "audio": [
        "16",
        0
      ]
    },
    "class_type": "MelBandRoFormerSampler",
    "_meta": {
      "title": "Mel-Band RoFormer Sampler"
    }
  },
  "105": {
    "inputs": {
      "api_baseurl": "https://api.deepseek.com",
      "api_key": "",
      "model": "deepseek-v4-flash",
      "role": [
        "109",
        0
      ],
      "prompt": [
        "36",
        0
      ],
      "temperature": 0.5,
      "seed": 1761935326
    },
    "class_type": "RH_LLMAPI_NODE",
    "_meta": {
      "title": "Runninghub LLM API Node"
    }
  },
  "107": {
    "inputs": {
      "text": "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.",
      "anything": [
        "105",
        0
      ]
    },
    "class_type": "easy showAnything",
    "_meta": {
      "title": "Show Any"
    }
  },
  "108": {
    "inputs": {
      "text": "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."
    },
    "class_type": "CR Text",
    "_meta": {
      "title": "🔤 CR Text"
    }
  },
  "109": {
    "inputs": {
      "texts": [
        "108",
        0
      ],
      "find": "[Language]",
      "replace": [
        "110",
        0
      ]
    },
    "class_type": "ReplaceText",
    "_meta": {
      "title": "Replace Text (DEPRECATED)"
    }
  },
  "110": {
    "inputs": {
      "value": "English"
    },
    "class_type": "easy string",
    "_meta": {
      "title": "输入目标语言"
    }
  },
  "176": {
    "inputs": {
      "tempo_limit": 2,
      "mini_gap_ms": 10,
      "srt_items": [
        "177",
        1
      ],
      "audios": [
        "268",
        0
      ]
    },
    "class_type": "VoiceBridgeAudioListMergerBySRT",
    "_meta": {
      "title": "VoiceBridge Audio List Merger by SRT"
    }
  },
  "177": {
    "inputs": {
      "srt_string": [
        "105",
        0
      ]
    },
    "class_type": "VoiceBridgeSRTSplitter",
    "_meta": {
      "title": "VoiceBridge SRT Splitter"
    }
  },
  "179": {
    "inputs": {
      "text": "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",
      "anything": [
        "176",
        1
      ]
    },
    "class_type": "easy showAnything",
    "_meta": {
      "title": "Show Any"
    }
  },
  "180": {
    "inputs": {
      "filename_prefix": "audio/ComfyUI",
      "quality": "V0",
      "audioUI": "",
      "audio": [
        "251",
        0
      ]
    },
    "class_type": "SaveAudioMP3",
    "_meta": {
      "title": "Save Audio (MP3)"
    }
  },
  "206": {
    "inputs": {
      "control_instruction": "",
      "text": [
        "177",
        0
      ],
      "cfg_value": 2,
      "inference_steps": 10,
      "seed": 220751697769047,
      "ultimate_clone": true,
      "reference_audio_text": [
        "264",
        0
      ],
      "normalize_text": false,
      "denoise_reference": false,
      "max_len": 4096,
      "retry_badcase": true,
      "model": [
        "207",
        0
      ],
      "reference_audio": [
        "261",
        0
      ]
    },
    "class_type": "RunningHub_VoxCPM_Generate",
    "_meta": {
      "title": "RunningHub VoxCPM Generate Speech"
    }
  },
  "207": {
    "inputs": {
      "model_name": "VoxCPM2",
      "optimize": false,
      "lora_name": "None"
    },
    "class_type": "RunningHub_VoxCPM_LoadModel",
    "_meta": {
      "title": "RunningHub VoxCPM Load Model"
    }
  },
  "214": {
    "inputs": {
      "srt_string": [
        "179",
        0
      ],
      "filename_prefix": "VoiceBridge/subtitle"
    },
    "class_type": "SaveSRTFromString",
    "_meta": {
      "title": "Save SRT From String"
    }
  },
  "251": {
    "inputs": {
      "audio_1": [
        "176",
        0
      ],
      "audio_2": [
        "99",
        1
      ]
    },
    "class_type": "MergeAudioMW",
    "_meta": {
      "title": "Merge Audio"
    }
  },
  "261": {
    "inputs": {
      "any_01": [
        "46",
        0
      ]
    },
    "class_type": "Any Switch (rgthree)",
    "_meta": {
      "title": "Any Switch (rgthree)"
    }
  },
  "264": {
    "inputs": {
      "any_01": [
        "45",
        1
      ]
    },
    "class_type": "Any Switch (rgthree)",
    "_meta": {
      "title": "Any Switch (rgthree)"
    }
  },
  "268": {
    "inputs": {
      "start_index": 0.30000000000000004,
      "duration": 100.00000000000001,
      "audio": [
        "206",
        0
      ]
    },
    "class_type": "TrimAudioDuration",
    "_meta": {
      "title": "Trim Audio Duration"
    }
  }
}