How to extract YouTube transcripts in a workflow

{
  "name": "YouTube transcripts to Notion",
  "nodes": [
    {
      "id": "f9a2555a-34fc-4eb6-af83-9fab894e14e3",
      "name": "Run by hand",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        0,
        0
      ],
      "parameters": {}
    },
    {
      "id": "3eb67cba-4372-4380-a012-2599c8ad1ad3",
      "name": "Every day",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.2,
      "position": [
        0,
        200
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "triggerAtHour": 8
            }
          ]
        }
      },
      "notes": "Activate the workflow to run on this schedule."
    },
    {
      "id": "f8f70f7e-55a1-426d-a972-f4a42f93b6cb",
      "name": "Run Apify Actor",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        260,
        100
      ],
      "parameters": {
        "method": "POST",
        "url": "https://api.apify.com/v2/actors/nimbryxo-studio~youtube-caption-and-whisper-ai-transcript/run-sync-get-dataset-items",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "{\n  \"mode\": \"videos\",\n  \"videoUrls\": [\n    \"https://www.youtube.com/watch?v=jNQXAC9IVRw\"\n  ],\n  \"includeAutoGenerated\": true,\n  \"useWhisper\": true,\n  \"whisperModel\": \"tiny\",\n  \"includeWordTimings\": false,\n  \"proxyCountry\": \"GB\"\n}",
        "options": {
          "timeout": 310000
        }
      },
      "notes": "Actor: nimbryxo-studio/youtube-caption-and-whisper-ai-transcript. Select a Header Auth credential: name Authorization, value Bearer + your Apify token. Edit the JSON body to change the input.",
      "notesInFlow": false
    },
    {
      "id": "152fae2a-ee17-48ae-ab4c-e4d3446a182b",
      "name": "Only records not sent before",
      "type": "n8n-nodes-base.removeDuplicates",
      "typeVersion": 2,
      "position": [
        500,
        100
      ],
      "parameters": {
        "operation": "removeItemsSeenInPreviousExecutions",
        "logic": "removeItemsWithAlreadySeenKeyValues",
        "dedupeValue": "={{ $json.video_id }}",
        "options": {
          "scope": "node",
          "historySize": 10000
        }
      },
      "notes": "Remembers each video_id it has passed on (up to 10,000) across runs, so a record is sent once. Needs n8n 1.64 or later."
    },
    {
      "id": "e318ffea-1be5-4c08-a183-cd85021aedaf",
      "name": "Keep main fields",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        740,
        100
      ],
      "parameters": {
        "jsCode": "// Keeps the Actor's main fields as flat, spreadsheet-safe values.\nconst columns = [\"title\",\"views\",\"canonicalUrl\",\"inputUrl\",\"video_id\",\"channel_name\",\"publishedAt\",\"transcript_language\",\"segment_count\",\"success\",\"transcript_available\",\"transcript_source\",\"accessStatus\",\"errorCode\",\"full_text\"];\n// A dotted name such as author.name reads the nested value.\nconst read = (obj, key) => (key in obj ? obj[key] : key.split('.').reduce((v, part) => (v && typeof v === 'object' ? v[part] : undefined), obj));\nreturn $input.all().map((item) => {\n  const row = {};\n  const present = columns.filter((key) => read(item.json, key) !== undefined);\n  // A record shaped differently from the published schema keeps its own fields rather than arriving blank.\n  for (const key of present.length >= 2 ? present : Object.keys(item.json)) {\n    const value = read(item.json, key);\n    row[key] = value === null || value === undefined ? '' : typeof value === 'object' ? JSON.stringify(value) : value;\n  }\n  return { json: row };\n});"
      }
    },
    {
      "id": "8a32b812-4547-4a68-aa4f-0dd12f22f1c3",
      "name": "Send to Notion",
      "type": "n8n-nodes-base.notion",
      "typeVersion": 2.2,
      "position": [
        980,
        100
      ],
      "parameters": {
        "resource": "databasePage",
        "databaseId": {
          "__rl": true,
          "value": "",
          "mode": "list"
        },
        "title": "={{ [$json.title].filter((v) => v !== undefined && v !== null && v !== '').join(': ') || 'Untitled' }}",
        "propertiesUi": {
          "propertyValues": []
        },
        "blockUi": {
          "blockValues": [
            {
              "type": "paragraph",
              "textContent": "={{ [[\"views\", $json.views], [\"canonicalUrl\", $json.canonicalUrl], [\"inputUrl\", $json.inputUrl], [\"video_id\", $json.video_id], [\"channel_name\", $json.channel_name], [\"publishedAt\", $json.publishedAt], [\"transcript_language\", $json.transcript_language], [\"segment_count\", $json.segment_count], [\"success\", $json.success], [\"transcript_available\", $json.transcript_available]].filter(([, v]) => v !== undefined && v !== null && v !== '').map(([k, v]) => k + ': ' + (typeof v === 'object' ? JSON.stringify(v) : v)).join(' | ').slice(0, 1900) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(0, 1900) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(1900, 3800) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(3800, 5700) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(5700, 7600) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(7600, 9500) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(9500, 11400) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(11400, 13300) || ' ' }}"
            },
            {
              "type": "paragraph",
              "textContent": "={{ String($json.full_text ?? '').slice(13300, 15200) || ' ' }}"
            }
          ]
        },
        "options": {}
      },
      "notes": "Pick your Notion database. Each page gets the record's main fields and the first 15200 characters of full_text as its content; map extra database properties if you want to filter on them."
    },
    {
      "id": "c04abe52-f683-4924-a56c-adc189e23f67",
      "name": "Setup",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        0,
        -370
      ],
      "parameters": {
        "content": "## YouTube Caption & Whisper AI Transcript Extractor\n\nSource: [nimbryxo-studio/youtube-caption-and-whisper-ai-transcript](https://apify.com/nimbryxo-studio/youtube-caption-and-whisper-ai-transcript) on Apify.\n\n1. In **Run Apify Actor**, create a Header Auth credential: name `Authorization`, value `Bearer YOUR_APIFY_TOKEN` with your token.\n2. Open **Send to Notion** and connect your Notion account.\n3. Edit the JSON body of **Run Apify Actor** to change the input.\n\nGenerated by recipeforagents.com. Validated, not executed: runs are billed to your Apify account.",
        "height": 340,
        "width": 460,
        "color": 6
      }
    }
  ],
  "connections": {
    "Run by hand": {
      "main": [
        [
          {
            "node": "Run Apify Actor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Every day": {
      "main": [
        [
          {
            "node": "Run Apify Actor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Run Apify Actor": {
      "main": [
        [
          {
            "node": "Only records not sent before",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Only records not sent before": {
      "main": [
        [
          {
            "node": "Keep main fields",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Keep main fields": {
      "main": [
        [
          {
            "node": "Send to Notion",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "pinData": {},
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "meta": {
    "templateCredsSetupCompleted": false
  },
  "tags": []
}