Automatische Erstellung von Blogs und KI-Bildern aus YouTube-Videos mit Dumpling AI und GPT-4o

Fortgeschritten

Dies ist ein Design, AI, Marketing-Bereich Automatisierungsworkflow mit 10 Nodes. Hauptsächlich werden Airtable, GoogleDrive, HttpRequest, ExtractFromFile, OpenAi und andere Nodes verwendet, kombiniert mit KI-Technologie für intelligente Automatisierung. Automatisiertes Erstellen von Blogs und KI-Bildern aus YouTube-Videos mit Dumpling AI und GPT-4o

Voraussetzungen
  • Airtable API Key
  • Google Drive API-Anmeldedaten
  • Möglicherweise sind Ziel-API-Anmeldedaten erforderlich
  • OpenAI API Key
Workflow-Vorschau
Visualisierung der Node-Verbindungen, mit Zoom und Pan
Workflow exportieren
Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n
{
  "id": "kyDSmFJkvi8CYHh2",
  "meta": {
    "instanceId": "a1ae5c8dc6c65e674f9c3947d083abcc749ef2546dff9f4ff01de4d6a36ebfe6",
    "templateCredsSetupCompleted": true
  },
  "name": "Auto-Generate Blog & AI Image from YouTube Videos with Dumpling AI & GPT-4o",
  "tags": [],
  "nodes": [
    {
      "id": "7847f8a8-a60e-4b2c-afa1-8d586cb42d5c",
      "name": "Überwachungsordner für neue YouTube-Videos",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        -2960,
        -420
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1mde_V0ePcJEebVydygVKT7GDiABjj2A4",
          "cachedResultName": "Youtube Videos"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "B0Hulh0j065xznhI",
          "name": "Google Drive account 2"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "cee77d1b-a91a-4fae-b5ae-eac34a9b0a03",
      "name": "Video-Datei herunterladen",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -2740,
        -420
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "B0Hulh0j065xznhI",
          "name": "Google Drive account 2"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "7b5ae3f4-d89d-4506-985d-a4c2afc5c0f5",
      "name": "Heruntergeladenes Video in Base64 konvertieren",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        -2520,
        -420
      ],
      "parameters": {
        "options": {},
        "operation": "binaryToPropery"
      },
      "typeVersion": 1
    },
    {
      "id": "e94c073a-e8e3-4b7e-9b86-21f7568b98cb",
      "name": "Video mit Dumpling AI transkribieren (vollständiges Transkript)",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -2300,
        -420
      ],
      "parameters": {
        "url": "https://app.dumplingai.com/api/v1/extract-video",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"inputMethod\": \"base64\",\n  \"video\": \"{{ $json.data }}\",\n  \"prompt\": \"Please transcribe the entire audio content of this video. I need a clear, complete, and accurate transcript of everything that was said, without summarizing or skipping any part. Include all spoken words, even fillers or pauses like 'um' or 'uh', if present. Format the transcript in clean readable text, broken into paragraphs where appropriate.\",\n  \"jsonMode\": \"false\"\n}\n",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpBasicAuth": {
          "id": "ZqOKe2AhRqsTlTR1",
          "name": "n8n connections"
        },
        "httpHeaderAuth": {
          "id": "RLFzAcGRepr5eXZB",
          "name": "n8n"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "29e09351-0d8e-40c4-8a41-d00bff9e93a4",
      "name": "Blog & Bild-Prompt mit GPT-4o generieren",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        -2080,
        -420
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o",
          "cachedResultName": "GPT-4O"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "=You are an experienced blog writer and creative AI assistant. Based on the transcript I will provide, generate:\n\nA blog post that summarizes and expands on the key message of the video in a clear, engaging, and human tone.\n\nAn image prompt for AI image generation that visually supports the content of the blog post.\n\nBlog Post Guidelines:\n\nThe blog post should be written in a natural and conversational tone.\n\nIt must start with a strong opening paragraph that hooks the reader.\n\nFollow with 2 to 4 short paragraphs that explain or expand on the main ideas in the transcript.\n\nEnd with a clear conclusion or takeaway that wraps up the message or encourages readers to take action.\n\nDo not use overly technical or robotic language. Keep it clear and useful for the average reader.\n\nImage Prompt Guidelines:\n\nCreate a short, descriptive image prompt that visually represents the core message of the blog.\n\nThe image prompt should be suitable for AI image generation models like \nFLUX.1-pro.\n\nIt should be visually specific, using descriptive words that reflect the theme and tone of the blog.\n\nReturn your response in this exact JSON format:\n\n{\n  \"blog_post\": \"Your full blog content here\",\n  \"image_prompt\": \"Your image generation prompt here\"\n}"
            },
            {
              "content": "=Here is the transcript to work with:[{{ $json.results }} ] "
            }
          ]
        },
        "jsonOutput": true
      },
      "credentials": {
        "openAiApi": {
          "id": "fdhWALG84tBLgSZT",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "d68ab832-0c22-4ee7-8406-f1aba6911f70",
      "name": "Visual aus Blog-Prompt mit Dumpling AI generieren",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -1700,
        -420
      ],
      "parameters": {
        "url": "https://app.dumplingai.com/api/v1/generate-ai-image",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"model\": \"FLUX.1-pro\",\n  \"input\": {\n    \"prompt\": \"{{ $json.message.content.image_prompt }}\",\n    \"width\": 1024,\n    \"height\": 576,\n    \"aspect_ratio\": \"16:9\"\n  }\n}\n",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "RLFzAcGRepr5eXZB",
          "name": "n8n"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "34b5a7a2-2cab-49a4-a905-dd6611de33f1",
      "name": "Blogbeitrag in Airtable speichern",
      "type": "n8n-nodes-base.airtable",
      "position": [
        -1480,
        -420
      ],
      "parameters": {
        "base": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://airtable.com/appPSvSKdA6075xJC",
          "cachedResultName": "Testing n8n"
        },
        "table": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://airtable.com/appPSvSKdA6075xJC/tblboiRp54hqA813K",
          "cachedResultName": "social post"
        },
        "columns": {
          "value": {
            "Content": "={{ $('Generate Blog & Image Prompt using GPT-4o').item.json.message.content.blog_post }}"
          },
          "schema": [
            {
              "id": "ID",
              "type": "string",
              "display": true,
              "removed": true,
              "readOnly": true,
              "required": false,
              "displayName": "ID",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Content",
              "type": "string",
              "display": true,
              "removed": false,
              "readOnly": false,
              "required": false,
              "displayName": "Content",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Attachments",
              "type": "array",
              "display": true,
              "removed": false,
              "readOnly": false,
              "required": false,
              "displayName": "Attachments",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "create"
      },
      "credentials": {
        "airtableTokenApi": {
          "id": "H8PVkBgUPCcUhhRC",
          "name": "Airtable Personal Access Token account"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "cc6c3c98-d639-4bd4-b727-3556e33c3397",
      "name": "Blogbeitragsbild in Airtable hochladen",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -1260,
        -420
      ],
      "parameters": {
        "url": "=https://api.airtable.com/v0///{{ $json.id }}",
        "method": "PATCH",
        "options": {},
        "jsonBody": "={\n  \"fields\": {\n    \"Attachments\": [\n      {\n        \"url\": \"{{ $('Generate Blog & Image Prompt using GPT-4o').item.json.message.content.image_prompt }}\"\n      }\n    ]\n  }\n}\n",
        "sendBody": true,
        "sendHeaders": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "headerParameters": {
          "parameters": [
            {}
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "VyzU59iFznTo7K6r",
          "name": "Airtable Connection"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "aa4fb418-c654-413e-986f-df5bad418703",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2960,
        -620
      ],
      "parameters": {
        "width": 700,
        "height": 240,
        "content": "### 🎥 From Video Upload to Blog Prompt\n\nThis part of the workflow starts when a new video is added to a designated Google Drive folder. It downloads the video and converts it into base64 format. That base64 video is then sent to Dumpling AI’s `extract-video` endpoint, which transcribes the entire audio content. The transcription is passed to GPT-4o, which writes a full blog post and also creates a descriptive image prompt based on the video's message.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "8a379ab7-b7ba-409f-a072-c3e0c7e20f7e",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2040,
        -620
      ],
      "parameters": {
        "width": 820,
        "height": 260,
        "content": "### 📝 Generate Image and Save Blog to Airtable\n\nThe AI-generated image prompt is sent to Dumpling AI’s `generate-ai-image` endpoint (model FLUX.1-pro) to produce a visual that aligns with the blog post. The blog content is stored in Airtable under the `Content` field. Finally, the image prompt is also patched into the Airtable record under `Attachments` to complete the post entry for social use or publishing.\n"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "41c42227-95ae-4535-be56-1cc8a71490ac",
  "connections": {
    "cee77d1b-a91a-4fae-b5ae-eac34a9b0a03": {
      "main": [
        [
          {
            "node": "7b5ae3f4-d89d-4506-985d-a4c2afc5c0f5",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "34b5a7a2-2cab-49a4-a905-dd6611de33f1": {
      "main": [
        [
          {
            "node": "cc6c3c98-d639-4bd4-b727-3556e33c3397",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "7b5ae3f4-d89d-4506-985d-a4c2afc5c0f5": {
      "main": [
        [
          {
            "node": "e94c073a-e8e3-4b7e-9b86-21f7568b98cb",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "7847f8a8-a60e-4b2c-afa1-8d586cb42d5c": {
      "main": [
        [
          {
            "node": "cee77d1b-a91a-4fae-b5ae-eac34a9b0a03",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "29e09351-0d8e-40c4-8a41-d00bff9e93a4": {
      "main": [
        [
          {
            "node": "d68ab832-0c22-4ee7-8406-f1aba6911f70",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d68ab832-0c22-4ee7-8406-f1aba6911f70": {
      "main": [
        [
          {
            "node": "34b5a7a2-2cab-49a4-a905-dd6611de33f1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "e94c073a-e8e3-4b7e-9b86-21f7568b98cb": {
      "main": [
        [
          {
            "node": "29e09351-0d8e-40c4-8a41-d00bff9e93a4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Häufig gestellte Fragen

Wie verwende ich diesen Workflow?

Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.

Für welche Szenarien ist dieser Workflow geeignet?

Fortgeschritten - Design, Künstliche Intelligenz, Marketing

Ist es kostenpflichtig?

Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.

Verwandte Workflows

Automatische Erstellung von Facebook-Posts aus Video-Einblicken mit Dumpling AI + GPT-4o
Automatisiertes Erstellen von Facebook-Posts aus Video-Insights mit Dumpling AI + GPT-4o
Google Drive
Http Request
Google Sheets
+
Google Drive
Http Request
Google Sheets
8 NodesYang
Künstliche Intelligenz
Generierung von Titeln mit Dumpling AI + GPT-4o basierend auf Autovervollständigungs-Vorschlägen
Mit Dumpling AI + GPT-4o aus Vorschlägen der Autocomplete-Features Titel generieren
Set
Split Out
Http Request
+
Set
Split Out
Http Request
8 NodesYang
Design
AI-Eisbrecher-Inhaltsgenerator: Websites mit Dumpling AI erfassen und in Airtable speichern
AI-Eisbrecher-Inhaltsgenerator: Websites mit Dumpling AI erfassen und in Airtable speichern
Wait
Airtable
Http Request
+
Wait
Airtable
Http Request
9 NodesYang
Künstliche Intelligenz
Podcast-Erstellung automatisch aus YouTube-Videos mit Hilfe von Dumpling AI und GPT-4o
Automatisches Podcast-Erstellen mit Dumpling AI und GPT-4o aus YouTube-Untertiteln
Airtable
Http Request
Open Ai
+
Airtable
Http Request
Open Ai
5 NodesYang
Künstliche Intelligenz
Produktinformationen aus Webseiten-Screenshots mit Dumpling AI und GPT-4o extrahieren
Extraktion von Produktinformationen aus Webseiten Screenshots mittels Dumpling AI und GPT-4o
Split Out
Google Drive
Http Request
+
Split Out
Google Drive
Http Request
11 NodesYang
Künstliche Intelligenz
Dumpling AI verwenden, um Rechnungsdaten aus Google Drive in Sheets zu extrahieren
Mit Dumpling AI Rechnungsdaten von Google Drive extrahieren und in Sheets speichern
Code
Split Out
Google Drive
+
Code
Split Out
Google Drive
8 NodesYang
Künstliche Intelligenz
Workflow-Informationen
Schwierigkeitsgrad
Fortgeschritten
Anzahl der Nodes10
Kategorie3
Node-Typen7
Schwierigkeitsbeschreibung

Für erfahrene Benutzer, mittelkomplexe Workflows mit 6-15 Nodes

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34