Transcribe and Analyze Meetings or Podcasts with ElevenLabs

{
  "id": "7igUJFLIXoP9aAKl",
  "meta": {
    "instanceId": "a4bfc93e975ca233ac45ed7c9227d84cf5a2329310525917adaf3312e10d5462",
    "templateCredsSetupCompleted": true
  },
  "name": "Transcribe and Analyze Meetings or Podcasts with ElevenLabs",
  "tags": [],
  "nodes": [
    {
      "id": "3636a64e-7b0e-4ee3-8837-d7ecb59a29a9",
      "name": "When clicking ‘Execute workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -576,
        96
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "41fb00ed-9bd1-495a-935b-714d562ab539",
      "name": "Loop Over Items",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        -144,
        96
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "2fa6fdc5-3bd7-4e17-9f23-90c32c6989d6",
      "name": "Call 'ElevenLabs Text-to-Speech'",
      "type": "n8n-nodes-base.executeWorkflow",
      "position": [
        544,
        336
      ],
      "parameters": {
        "mode": "each",
        "options": {
          "waitForSubWorkflow": true
        },
        "workflowId": {
          "__rl": true,
          "mode": "id",
          "value": "7igUJFLIXoP9aAKl"
        },
        "workflowInputs": {
          "value": {
            "text": "={{ $('Speech-to-Text').item.json.text }}"
          },
          "schema": [
            {
              "id": "text",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "text",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [
            "text"
          ],
          "attemptToConvertTypes": true,
          "convertFieldsToString": true
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "576849a8-b2ab-4b17-b96a-c912f027c709",
      "name": "When Executed by Another Workflow",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "position": [
        -544,
        704
      ],
      "parameters": {
        "workflowInputs": {
          "values": [
            {
              "name": "text"
            }
          ]
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "0d9ec033-f75c-4ad4-9d70-fcfd9045e363",
      "name": "Get audio urls",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        -384,
        96
      ],
      "parameters": {
        "options": {},
        "filtersUI": {
          "values": [
            {
              "lookupColumn": "DONE"
            }
          ]
        },
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU/edit#gid=0",
          "cachedResultName": "Foglio1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU/edit?usp=drivesdk",
          "cachedResultName": "Elevenlabs Speech-to-Text"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "JYR6a64Qecd6t8Hb",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.7
    },
    {
      "id": "b486796d-9cb8-45ab-8a0a-7d6ba1af087b",
      "name": "Speech-to-Text",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        112,
        112
      ],
      "parameters": {
        "url": "https://api.elevenlabs.io/v1/speech-to-text",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "contentType": "form-urlencoded",
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "model_id",
              "value": "scribe_v1"
            },
            {
              "name": "cloud_storage_url",
              "value": "={{ $json['AUDIO URL'] }}"
            },
            {
              "name": "tag_audio_events",
              "value": "true"
            }
          ]
        },
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "cuOCiacID6OxWFUF",
          "name": "ElevenLabs API"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "ac72a840-ce27-490c-ab7f-003b5ec3684a",
      "name": "Update row",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        112,
        336
      ],
      "parameters": {
        "columns": {
          "value": {
            "DONE": "x",
            "DOCS ID": "={{ $('Create Doc').item.json.id }}",
            "row_number": "={{ $('Loop Over Items').item.json.row_number }}"
          },
          "schema": [
            {
              "id": "AUDIO URL",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "AUDIO URL",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "DONE",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "DONE",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "DOCS ID",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "DOCS ID",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "row_number",
              "type": "number",
              "display": true,
              "removed": false,
              "readOnly": true,
              "required": false,
              "displayName": "row_number",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [
            "row_number"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "update",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU/edit#gid=0",
          "cachedResultName": "Foglio1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU/edit?usp=drivesdk",
          "cachedResultName": "Elevenlabs Speech-to-Text"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "JYR6a64Qecd6t8Hb",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.7
    },
    {
      "id": "a05956e3-2151-4897-94f5-8b63972a1ada",
      "name": "Transcript Analysis",
      "type": "@n8n/n8n-nodes-langchain.googleGemini",
      "position": [
        -224,
        704
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "models/gemini-2.5-pro",
          "cachedResultName": "models/gemini-2.5-pro"
        },
        "options": {
          "systemMessage": "=# Meeting Transcript Analysis AI Agent - System Prompt\n\nYou are an expert AI agent specialized in analyzing and summarizing transcriptions from meetings, podcasts, interviews, webinars, and other audio/video content. Your primary function is to extract meaningful insights and create comprehensive summaries from spoken content that has been converted to text.\n\n## Core Responsibilities\n\n**Primary Function**: Analyze and summarize transcribed content with high accuracy and relevance, focusing on key information extraction and actionable insights.\n\n## Analysis Capabilities\n\n### Content Types You Handle\n- Business meetings (team meetings, board meetings, client calls)\n- Podcasts and interviews\n- Webinars and presentations  \n- Conference calls and video conferences\n- Training sessions and workshops\n- Sales calls and customer interactions\n- Academic lectures and seminars\n\n### Key Analysis Areas\n- **Main Topics & Themes**: Identify central discussion points and recurring themes\n- **Key Decisions**: Extract decisions made, consensus reached, and resolutions\n- **Action Items**: Identify tasks assigned, deadlines, and responsibilities\n- **Key Participants**: Note important speakers and their contributions\n- **Important Quotes**: Capture significant statements and insights\n- **Follow-up Items**: Identify what needs to happen next\n- **Conflicts or Issues**: Note disagreements, concerns, or problems discussed\n\n## Summary Structure Guidelines\n\nWhen summarizing transcripts, organize your output using this structure:\n\n### Executive Summary\n- Brief overview of the main purpose and outcome (2-3 sentences)\n\n### Key Discussion Points\n- Main topics covered in order of importance\n- Context and background information when relevant\n\n### Decisions Made\n- Clear list of decisions reached\n- Who made the decisions and any voting/consensus details\n\n### Action Items\n- Specific tasks identified\n- Assigned person/team (when mentioned)\n- Deadlines or timeframes (when specified)\n\n### Important Insights\n- Notable quotes, ideas, or revelations\n- Expert opinions or recommendations shared\n\n### Next Steps\n- Follow-up meetings or actions planned\n- Unresolved items requiring future attention\n\n## Quality Standards\n\n### Accuracy Requirements\n- Maintain fidelity to the original content\n- Do not infer information not present in the transcript\n- Clearly distinguish between stated facts and implied meanings\n- Preserve the context and tone when relevant\n\n### Clarity Standards\n- Use clear, professional language\n- Organize information logically\n- Highlight the most important information\n- Make summaries scannable with appropriate headers\n\n### Completeness Guidelines\n- Cover all major topics discussed\n- Include all action items and decisions\n- Note important participant contributions\n- Capture timeline and sequence when relevant\n\n## Special Handling Instructions\n\n### For Meeting Transcripts\n- Focus on business outcomes and decisions\n- Highlight resource allocation and budget discussions\n- Note attendance and key participant roles\n- Identify meeting effectiveness and any process issues\n\n### For Podcasts/Interviews\n- Emphasize key insights and expert opinions\n- Note interesting anecdotes or case studies\n- Highlight actionable advice or recommendations\n- Capture the guest's background and credentials when relevant\n\n### For Technical Content\n- Explain complex concepts in accessible language\n- Note technical specifications or requirements\n- Highlight implementation details and timelines\n- Identify technical challenges or solutions discussed\n\n## Response Formatting\n\n- Use markdown formatting for better readability\n- Apply consistent header hierarchy\n- Use bullet points for lists and action items\n- Bold key terms and important information\n- Include relevant timestamps when available in the source\n\n## Adaptive Analysis\n\nAdjust your analysis depth and focus based on:\n- Content length and complexity\n- Apparent purpose of the original meeting/content\n- Level of technical detail present\n- Stakeholder types involved\n- Urgency indicators in the content\n\n## Limitations Acknowledgment\n\nWhen encountering unclear audio transcription, multiple speakers, or ambiguous content:\n- Note areas where the transcript may be unclear\n- Indicate when speaker identification is uncertain\n- Flag potential transcription errors that affect meaning\n- Suggest areas that may need clarification from participants\n\nYour goal is to transform raw transcribed content into organized, actionable summaries that save time and ensure nothing important is mi"
        },
        "messages": {
          "values": [
            {
              "content": "=Full transcript:\n{{ $json.text }}"
            }
          ]
        }
      },
      "credentials": {
        "googlePalmApi": {
          "id": "AaNPKXAphyMzRgfA",
          "name": "Google Gemini(PaLM) (Eure)"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "6a8e5bd2-8a45-4f9f-bd57-e80c071dbd67",
      "name": "Send email",
      "type": "n8n-nodes-base.gmail",
      "position": [
        560,
        704
      ],
      "webhookId": "a9460f49-968a-412d-8805-9c583f23c52f",
      "parameters": {
        "sendTo": "YOUR_EMAIL_ADDRESS",
        "message": "={{ $json.data }}",
        "options": {
          "appendAttribution": false
        },
        "subject": "=[N8N] Recap",
        "emailType": "text"
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "nyuHvSX5HuqfMPlW",
          "name": "Gmail account (n3w.it)"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "5ba1820c-8aef-435f-88e1-e6242f50ad18",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -592,
        -672
      ],
      "parameters": {
        "color": 3,
        "width": 704,
        "height": 320,
        "content": "## Transcribe and Analyze Meetings or Podcasts (audio/video) using ElevenLabs Speech-to-Text\n\nThis model excels in scenarios requiring accurate speech-to-text conversion:\n- Transcription Services: Perfect for converting audio/video content to text\n- Meeting Documentation: Ideal for capturing and documenting conversations\n- Content Analysis: Well-suited for audio content processing and analysis\n- Multilingual Recognition: Supports accurate transcription across 99 languages\n\nFiles up to 3 GB in size and up to 10 hours in duration are supported.\n\nThis API supports uploading both audio and video files for transcription.\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "b2a10f86-4613-47a2-b733-3e85083b3bba",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -592,
        -320
      ],
      "parameters": {
        "color": 5,
        "width": 704,
        "height": 176,
        "content": "## STEP 1\n- Register for FREE to [Elevenlabs](https://try.elevenlabs.io/ahkbf00hocnu)\n- Clone this [Sheet](https://docs.google.com/spreadsheets/d/1046e1OLfwiu1vfvnX_i2LP3yXOGL_87_BxyiXgkVmuU/edit?usp=sharing)\n- Insert the URL of the audio/video to be transcribed and analyzed in the 'Audio URL' column\n- Set the \"Auth Header\" in \"Speech-to-Text\" node. Name 'xi-api-key', Value 'API_KEY'"
      },
      "typeVersion": 1
    },
    {
      "id": "84780869-7d02-4d43-8831-9eac1409f79b",
      "name": "Markdown",
      "type": "n8n-nodes-base.markdown",
      "position": [
        208,
        704
      ],
      "parameters": {
        "mode": "markdownToHtml",
        "options": {},
        "markdown": "={{ $json.content.parts[0].text }}"
      },
      "typeVersion": 1
    },
    {
      "id": "6f182a94-bfe7-4718-b323-dc0be3b503b8",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        48,
        32
      ],
      "parameters": {
        "width": 224,
        "height": 240,
        "content": "## Transcript"
      },
      "typeVersion": 1
    },
    {
      "id": "ab04db7f-43f8-43aa-a476-b19ca55f8b5e",
      "name": "Add Transcript to Doc",
      "type": "n8n-nodes-base.googleDocs",
      "position": [
        544,
        112
      ],
      "parameters": {
        "actionsUi": {
          "actionFields": [
            {
              "text": "={{ $('Speech-to-Text').item.json.text }}",
              "action": "insert"
            }
          ]
        },
        "operation": "update",
        "documentURL": "={{ $json.id }}"
      },
      "credentials": {
        "googleDocsOAuth2Api": {
          "id": "LpmDV1ry0BPLvW8b",
          "name": "Google Docs account"
        }
      },
      "typeVersion": 2
    },
    {
      "id": "70c2a0e6-7d19-457a-ad28-3bb6dafa7142",
      "name": "Create Doc",
      "type": "n8n-nodes-base.googleDocs",
      "position": [
        320,
        112
      ],
      "parameters": {
        "title": "={{ $json.transcription_id }}",
        "folderId": "1tkCr7xdraoZwsHqeLm7FZ4aRWY94oLbZ"
      },
      "credentials": {
        "googleDocsOAuth2Api": {
          "id": "LpmDV1ry0BPLvW8b",
          "name": "Google Docs account"
        }
      },
      "typeVersion": 2
    },
    {
      "id": "0fcf062e-5603-46bc-bf4f-3d62cf1640a0",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -304,
        640
      ],
      "parameters": {
        "width": 400,
        "height": 240,
        "content": "## Analysis"
      },
      "typeVersion": 1
    },
    {
      "id": "e4ff9aae-a943-4763-a4ac-3db77532d75e",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -592,
        -112
      ],
      "parameters": {
        "color": 5,
        "width": 704,
        "height": 96,
        "content": "## STEP 2\n- Set YOUR_EMAIL_ADDRESS in \"Send email\" node"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "b6fd2daf-7117-4396-b0a9-135fd17c71d3",
  "connections": {
    "Markdown": {
      "main": [
        [
          {
            "node": "Send email",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create Doc": {
      "main": [
        [
          {
            "node": "Add Transcript to Doc",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Update row": {
      "main": [
        [
          {
            "node": "Call 'ElevenLabs Text-to-Speech'",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get audio urls": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Speech-to-Text": {
      "main": [
        [
          {
            "node": "Create Doc",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "Speech-to-Text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Transcript Analysis": {
      "main": [
        [
          {
            "node": "Markdown",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Add Transcript to Doc": {
      "main": [
        [
          {
            "node": "Update row",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Call 'ElevenLabs Text-to-Speech'": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When Executed by Another Workflow": {
      "main": [
        [
          {
            "node": "Transcript Analysis",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Execute workflow’": {
      "main": [
        [
          {
            "node": "Get audio urls",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}