Podcast-Erstellung automatisch aus YouTube-Videos mit Hilfe von Dumpling AI und GPT-4o

Anfänger

Dies ist ein AI, Marketing-Bereich Automatisierungsworkflow mit 5 Nodes. Hauptsächlich werden Airtable, HttpRequest, OpenAi, RssFeedReadTrigger und andere Nodes verwendet, kombiniert mit KI-Technologie für intelligente Automatisierung. Automatisches Podcast-Erstellen mit Dumpling AI und GPT-4o aus YouTube-Untertiteln

Voraussetzungen
  • Airtable API Key
  • 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": "I4j3HnFGPa5UWkIO",
  "meta": {
    "instanceId": "a1ae5c8dc6c65e674f9c3947d083abcc749ef2546dff9f4ff01de4d6a36ebfe6",
    "templateCredsSetupCompleted": true
  },
  "name": "Auto-Create Podcast from YouTube Video Transcript using Dumpling AI and GPT-4o",
  "tags": [],
  "nodes": [
    {
      "id": "d95bcf10-2bb4-4bfd-a8ad-4128a792deb8",
      "name": "Überwachung neuer YouTube-Videos per RSS",
      "type": "n8n-nodes-base.rssFeedReadTrigger",
      "position": [
        -500,
        -20
      ],
      "parameters": {
        "feedUrl": "https://rss.app/feeds/Vw076Uzh7bIinpci.xml",
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "a5492dab-f400-48d9-abd7-6c832d9d6816",
      "name": "Transkript aus YouTube-Video mit Dumpling AI abrufen",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -280,
        -20
      ],
      "parameters": {
        "url": "https://app.dumplingai.com/api/v1/get-youtube-transcript",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"videoUrl\": \"{{ $json.link }}\",\n  \"preferredLanguage\": \"en\"\n}\n",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "RLFzAcGRepr5eXZB",
          "name": "Dumpling AI-n8n"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "bce2bb18-c9ee-4165-ac27-5d300e354c7e",
      "name": "Transkript mit GPT-4o in Podcast-Skript umwandeln",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        -60,
        -20
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "chatgpt-4o-latest",
          "cachedResultName": "CHATGPT-4O-LATEST"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "=Instructions:\nYou are a professional transcript editor and podcast summarizer. For the transcript below, complete these tasks:\n\nLabel each speaker (e.g., Speaker 1:) and remove all filler words such as \"um,\" \"uh,\" \"you know,\" \"like,\" \"basically,\" \"actually,\" \"so.\"\n\nCombine the cleaned speaker labels and their text into one single string, clearly formatted.\n\nSummarize the key points of the conversation in 2–4 concise sentences.\n\nExtract or infer a short, relevant title based on the content.\n\nReturn your response strictly in the following JSON format:\n{\n  \"title\": \"Relevant podcast title here\",\n  \"cleaned_transcript\": \"Speaker 1: Cleaned text. Speaker 2: Cleaned text. (Continue in this format.)\",\n  \"summary\": \"Concise summary of the key points here.\"\n}"
            },
            {
              "content": "=\nHere’s the transcript:{{ $json.transcript }}"
            }
          ]
        },
        "jsonOutput": true
      },
      "credentials": {
        "openAiApi": {
          "id": "dd8NvMC6rvx8RITo",
          "name": "OpenAi account 2"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "7782b5a6-c842-41be-a5c5-9eaa28a0abd0",
      "name": "Podcast-Skript und Metadaten in Airtable speichern",
      "type": "n8n-nodes-base.airtable",
      "position": [
        300,
        -20
      ],
      "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/tbl4MDOqdNZweqXU9",
          "cachedResultName": "podcast"
        },
        "columns": {
          "value": {
            "Title": "={{ $json.message.content.title }}",
            "summary": "={{ $json.message.content.summary }}",
            "podcast transcript": "={{ $json.message.content.cleaned_transcript }}"
          },
          "schema": [
            {
              "id": "Title",
              "type": "string",
              "display": true,
              "removed": false,
              "readOnly": false,
              "required": false,
              "displayName": "Title",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "podcast transcript",
              "type": "string",
              "display": true,
              "removed": false,
              "readOnly": false,
              "required": false,
              "displayName": "podcast transcript",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "summary",
              "type": "string",
              "display": true,
              "removed": false,
              "readOnly": false,
              "required": false,
              "displayName": "summary",
              "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": "af143efd-be64-48fc-a405-173575289ed3",
      "name": "Notizzettel",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -500,
        -220
      ],
      "parameters": {
        "width": 640,
        "height": 280,
        "content": "### 🎙️ Auto-Create Podcast Script from YouTube Videos\n\nThis workflow starts by monitoring a YouTube RSS feed for new uploads. Once a new video is detected, Dumpling AI extracts the full transcript. GPT-4o then converts that transcript into a well-formatted podcast script, ensuring it’s clean, structured, and engaging. The final script along with the video title and summary is saved into Airtable, where it can be reviewed, edited, or used to produce an actual podcast episode.\n\nIdeal for creators repurposing video content into audio format.\n"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "0c39768f-93c9-42d7-8b9f-ca4e0ede2312",
  "connections": {
    "d95bcf10-2bb4-4bfd-a8ad-4128a792deb8": {
      "main": [
        [
          {
            "node": "a5492dab-f400-48d9-abd7-6c832d9d6816",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "a5492dab-f400-48d9-abd7-6c832d9d6816": {
      "main": [
        [
          {
            "node": "bce2bb18-c9ee-4165-ac27-5d300e354c7e",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "bce2bb18-c9ee-4165-ac27-5d300e354c7e": {
      "main": [
        [
          {
            "node": "7782b5a6-c842-41be-a5c5-9eaa28a0abd0",
            "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?

Anfänger - 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.

Workflow-Informationen
Schwierigkeitsgrad
Anfänger
Anzahl der Nodes5
Kategorie2
Node-Typen5
Schwierigkeitsbeschreibung

Für n8n-Anfänger, einfache Workflows mit 1-5 Nodes

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34