Macwhisper Transcript Processor

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "MacWhisper Transcript Processor",
  "nodes": [
    {
      "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        250,
        300
      ],
      "parameters": {
        "path": "transcript-processor",
        "httpMethod": "POST",
        "responseMode": "lastNode",
        "options": {}
      }
    },
    {
      "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
      "name": "Fragment Selection",
      "type": "@n8n/n8n-nodes-langchain.googleGemini",
      "typeVersion": 1,
      "position": [
        550,
        300
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gemini-2.0-flash-exp",
          "mode": "list",
          "cachedResultName": "gemini-2.0-flash-exp"
        },
        "options": {
          "systemMessage": "You are an expert content analyzer. Your task is to analyze podcast/stream transcripts and identify the 3-5 most engaging, emotional, or impactful fragments.\n\nFor each fragment, provide:\n- Start timecode in [HH:MM] format\n- End timecode in [HH:MM] format\n- Brief reason why this fragment is engaging\n\nFormat your response EXACTLY as:\n[HH:MM] -- [HH:MM]: Brief description of why this fragment is engaging\n\nSeparate each fragment with a blank line. Focus on moments with high emotional impact, insights, humor, or controversy."
        },
        "prompt": "=Analyze this transcript and identify the 3-5 most engaging fragments:\n\nTitle: {{ $json.body.title }}\n\nTranscript:\n{{ $json.body.transcript }}"
      }
    },
    {
      "id": "c3d4e5f6-a7b8-9012-cdef-123456789012",
      "name": "Get Fragment Text",
      "type": "@n8n/n8n-nodes-langchain.googleGemini",
      "typeVersion": 1,
      "position": [
        850,
        300
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gemini-2.0-flash-exp",
          "mode": "list",
          "cachedResultName": "gemini-2.0-flash-exp"
        },
        "options": {
          "systemMessage": "You are a precise transcript extractor. Your task is to extract the EXACT verbatim text for each fragment based on the provided timecodes.\n\nFor each fragment, output:\n[START_TIME] -- [END_TIME]\nEXACT VERBATIM TEXT FROM TRANSCRIPT\n---\n\nSeparate each fragment with '---' on its own line. Preserve all speaker names, pauses, and exact wording from the original transcript."
        },
        "prompt": "=Extract the exact verbatim text for these fragments from the transcript:\n\nFragments to extract:\n{{ $('Fragment Selection').item.json.message.content }}\n\nFull transcript:\n{{ $('Webhook').item.json.body.transcript }}\n\nProvide the exact text for each fragment, separated by '---'"
      }
    },
    {
      "id": "d4e5f6a7-b8c9-0123-def1-234567890123",
      "name": "Split Fragments",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1150,
        300
      ],
      "parameters": {
        "mode": "runOnceForAllItems",
        "jsCode": "const fragmentText = $input.item.json.message.content;\n\n// Split by --- delimiter\nconst fragments = fragmentText.split('---').filter(f => f.trim());\n\n// Parse each fragment\nconst parsedFragments = fragments.map((fragment, index) => {\n  const trimmed = fragment.trim();\n  \n  // Extract timecodes using regex [HH:MM] -- [HH:MM]\n  const timecodeMatch = trimmed.match(/\\[(\\d{2}:\\d{2})\\]\\s*--\\s*\\[(\\d{2}:\\d{2})\\]/);\n  \n  if (!timecodeMatch) {\n    return null;\n  }\n  \n  const start = timecodeMatch[1];\n  const end = timecodeMatch[2];\n  \n  // Extract content (everything after the timecode line)\n  const contentStart = trimmed.indexOf('\\n', timecodeMatch.index);\n  const content = contentStart !== -1 ? trimmed.substring(contentStart + 1).trim() : '';\n  \n  return {\n    json: {\n      fragmentIndex: index + 1,\n      start: start,\n      end: end,\n      content: content,\n      timecodeRange: `${start} -- ${end}`\n    }\n  };\n}).filter(f => f !== null);\n\nreturn parsedFragments;"
      }
    },
    {
      "id": "e5f6a7b8-c9d0-1234-ef12-345678901234",
      "name": "Create Subtitles",
      "type": "@n8n/n8n-nodes-langchain.googleGemini",
      "typeVersion": 1,
      "position": [
        1450,
        200
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gemini-2.0-flash-exp",
          "mode": "list",
          "cachedResultName": "gemini-2.0-flash-exp"
        },
        "options": {
          "systemMessage": "You are an expert subtitle creator. Convert the provided text into SRT subtitle format.\n\nRules:\n- Use ~140 words per minute timing\n- Each subtitle should be 1-2 lines maximum\n- Start from 00:00:00,000\n- Use proper SRT format:\n1\n00:00:00,000 --> 00:00:03,000\nFirst subtitle text\n\n2\n00:00:03,000 --> 00:00:06,000\nSecond subtitle text\n\nProvide ONLY the SRT content, nothing else."
        },
        "prompt": "=Convert this text into SRT subtitle format at ~140 words per minute:\n\n{{ $json.content }}"
      }
    },
    {
      "id": "f6a7b8c9-d0e1-2345-f123-456789012345",
      "name": "Convert to SRT",
      "type": "n8n-nodes-base.convertToFile",
      "typeVersion": 1.1,
      "position": [
        1750,
        200
      ],
      "parameters": {
        "mode": "jsonToText",
        "options": {
          "fileName": "=fragment_{{ $json.fragmentIndex }}.srt",
          "mimeType": "text/plain"
        },
        "jsonToText": {
          "inputDataFieldName": "={{ $('Create Subtitles').item.json.message.content }}"
        }
      }
    },
    {
      "id": "a7b8c9d0-e1f2-3456-1234-567890123456",
      "name": "Edit Fields",
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        1450,
        400
      ],
      "parameters": {
        "mode": "manual",
        "assignments": {
          "assignments": [
            {
              "id": "b8c9d0e1-f2a3-4567-2345-678901234567",
              "name": "formattedText",
              "value": "=Fragment {{ $json.fragmentIndex }}\nTimecode: {{ $json.timecodeRange }}\n\n{{ $json.content }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      }
    },
    {
      "id": "b8c9d0e1-f2a3-4567-2345-678901234567",
      "name": "Convert to TXT",
      "type": "n8n-nodes-base.convertToFile",
      "typeVersion": 1.1,
      "position": [
        1750,
        400
      ],
      "parameters": {
        "mode": "jsonToText",
        "options": {
          "fileName": "=timecodes_{{ $json.fragmentIndex }}.txt",
          "mimeType": "text/plain"
        },
        "jsonToText": {
          "inputDataFieldName": "={{ $json.formattedText }}"
        }
      }
    },
    {
      "id": "c9d0e1f2-a3b4-5678-3456-789012345678",
      "name": "Gmail",
      "type": "n8n-nodes-base.gmail",
      "typeVersion": 2.1,
      "position": [
        2050,
        200
      ],
      "parameters": {
        "operation": "send",
        "sendTo": "={{ $('Webhook').item.json.body.email || 'user@example.com' }}",
        "subject": "=Fragments - {{ $('Webhook').item.json.body.title }}",
        "message": "=Please find attached the SRT subtitle file for fragment {{ $json.fragmentIndex }}.\n\nTimecode: {{ $('Split Fragments').item.json.timecodeRange }}\n\nThis fragment was selected as one of the most engaging moments from the transcript.",
        "options": {
          "attachmentsUi": {
            "attachmentsBinary": [
              {
                "property": "data"
              }
            ]
          }
        }
      },
      "credentials": {
        "gmailOAuth2": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Fragment Selection",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fragment Selection": {
      "main": [
        [
          {
            "node": "Get Fragment Text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Fragment Text": {
      "main": [
        [
          {
            "node": "Split Fragments",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Fragments": {
      "main": [
        [
          {
            "node": "Create Subtitles",
            "type": "main",
            "index": 0
          },
          {
            "node": "Edit Fields",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create Subtitles": {
      "main": [
        [
          {
            "node": "Convert to SRT",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert to SRT": {
      "main": [
        [
          {
            "node": "Gmail",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Edit Fields": {
      "main": [
        [
          {
            "node": "Convert to TXT",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• gmailOAuth2

About this workflow

MacWhisper Transcript Processor. Uses googleGemini, gmail. Webhook trigger; 9 nodes.

Source: https://github.com/AI-agents-incubator/n8n-pilot/blob/main/tests/acceptance/output/macwhisper-generated.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.