Plaud Task Detection - Extract @mentions From Transcripts

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": "Plaud Task Detection - Extract @mentions from Transcripts",
  "nodes": [
    {
      "parameters": {
        "event": "audio_transcribe.completed"
      },
      "id": "trigger-1",
      "name": "Plaud Trigger",
      "type": "n8n-nodes-plaud.plaudTrigger",
      "typeVersion": 1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "resource": "workflow",
        "operation": "getResult",
        "workflowId": "={{ $json.workflow_id }}"
      },
      "id": "get-result-1",
      "name": "Get Workflow Result",
      "type": "n8n-nodes-plaud.plaud",
      "typeVersion": 1,
      "position": [
        460,
        300
      ],
      "credentials": {
        "plaudApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "// Extract transcription text from Plaud workflow result\nconst result = $input.first().json;\n\n// Navigate to the transcription data\n// Structure may vary based on Plaud API response\nconst transcription = result.tasks?.find(t => t.type === 'transcription')?.result?.text \n  || result.transcription?.text\n  || result.result?.transcription\n  || '';\n\nif (!transcription) {\n  return [{ json: { error: 'No transcription found in result', raw: result } }];\n}\n\n// Define mention patterns to search for\n// Add your team members here\nconst mentionPatterns = [\n  { name: 'Jade', pattern: /@jade/gi },\n  { name: 'Jay', pattern: /@jay(?!den)/gi },  // Match @jay but not @jayden\n  { name: 'Jayden', pattern: /@jayden/gi },\n];\n\n// Find all mentions and their surrounding context\nconst mentions = [];\nconst sentences = transcription.split(/[.!?]+/);\n\nfor (const sentence of sentences) {\n  for (const { name, pattern } of mentionPatterns) {\n    if (pattern.test(sentence)) {\n      mentions.push({\n        assignee: name,\n        context: sentence.trim(),\n        timestamp: new Date().toISOString(),\n      });\n    }\n  }\n}\n\n// Also extract potential action items (sentences with action verbs)\nconst actionVerbs = /\\b(need to|should|must|will|please|todo|action item|follow up|remind|schedule|book|call|email|send|review|check|update|create|fix|implement)\\b/gi;\n\nconst actionItems = sentences\n  .filter(s => actionVerbs.test(s))\n  .map(s => ({\n    type: 'action_item',\n    text: s.trim(),\n    timestamp: new Date().toISOString(),\n  }));\n\nreturn [{\n  json: {\n    workflowId: result.workflow_id || result.id,\n    totalMentions: mentions.length,\n    totalActionItems: actionItems.length,\n    mentions,\n    actionItems,\n    rawTranscription: transcription,\n  }\n}];"
      },
      "id": "code-1",
      "name": "Extract Tasks & Mentions",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        680,
        300
      ]
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict"
          },
          "conditions": [
            {
              "id": "condition-1",
              "leftValue": "={{ $json.totalMentions }}",
              "rightValue": 0,
              "operator": {
                "type": "number",
                "operation": "gt"
              }
            }
          ],
          "combinator": "or"
        },
        "options": {}
      },
      "id": "if-1",
      "name": "Has Mentions?",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2,
      "position": [
        900,
        300
      ]
    },
    {
      "parameters": {
        "mode": "raw",
        "jsonOutput": "={{ $json.mentions }}",
        "options": {}
      },
      "id": "split-1",
      "name": "Split Mentions",
      "type": "n8n-nodes-base.splitOut",
      "typeVersion": 1,
      "position": [
        1120,
        200
      ]
    },
    {
      "parameters": {
        "content": "## Plaud Task Detection Workflow\n\nThis workflow demonstrates how to:\n\n1. **Receive webhook events** from Plaud when transcriptions complete\n2. **Fetch the full result** using the workflow ID\n3. **Parse the transcription** to find @mentions and action items\n4. **Route notifications** based on who was mentioned\n\n### Setup Instructions\n\n1. Configure your Plaud API credentials\n2. Copy the webhook URL from the Plaud Trigger node\n3. Register the webhook URL in your [Plaud Developer Portal](https://platform.plaud.ai)\n4. Customize the mention patterns in the Code node\n5. Add notification nodes (Slack, Email, etc.) after the split\n\n### Customization\n\nEdit the `mentionPatterns` array in the Code node to match your team:\n\n```javascript\nconst mentionPatterns = [\n  { name: 'Alice', pattern: /@alice/gi },\n  { name: 'Bob', pattern: /@bob/gi },\n];\n```",
        "height": 520,
        "width": 380
      },
      "id": "note-1",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -100,
        140
      ]
    },
    {
      "parameters": {
        "content": "### Add Your Notifications Here\n\nConnect Slack, Email, or other notification nodes to alert team members when they're mentioned.\n\nExample Slack message:\n```\nNew task from meeting!\nAssignee: {{ $json.assignee }}\nContext: {{ $json.context }}\n```",
        "height": 220,
        "width": 300
      },
      "id": "note-2",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        1340,
        100
      ]
    },
    {
      "parameters": {},
      "id": "noop-1",
      "name": "No Mentions",
      "type": "n8n-nodes-base.noOp",
      "typeVersion": 1,
      "position": [
        1120,
        400
      ]
    }
  ],
  "connections": {
    "Plaud Trigger": {
      "main": [
        [
          {
            "node": "Get Workflow Result",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Workflow Result": {
      "main": [
        [
          {
            "node": "Extract Tasks & Mentions",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Tasks & Mentions": {
      "main": [
        [
          {
            "node": "Has Mentions?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Has Mentions?": {
      "main": [
        [
          {
            "node": "Split Mentions",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "No Mentions",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [
    {
      "name": "plaud",
      "createdAt": "2024-01-01T00:00:00.000Z",
      "updatedAt": "2024-01-01T00:00:00.000Z"
    },
    {
      "name": "task-detection",
      "createdAt": "2024-01-01T00:00:00.000Z",
      "updatedAt": "2024-01-01T00:00:00.000Z"
    }
  ],
  "triggerCount": 1,
  "updatedAt": "2024-01-01T00:00:00.000Z",
  "versionId": "1"
}

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.

• plaudApi

About this workflow

Plaud Task Detection - Extract @mentions from Transcripts. Uses n8n-nodes-plaud. Event-driven trigger; 8 nodes.

Source: https://github.com/iamruinous/n8n-nodes-plaud/blob/19218e932f24e6e9d8b68d400ddb78990241a134/examples/task-detection-workflow.json — original creator credit. Request a take-down →

More General workflows → · Browse all categories →

Related workflows

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