Podcast-Automatisierung

Experte

Dies ist ein Content Creation, Multimodal AI-Bereich Automatisierungsworkflow mit 16 Nodes. Hauptsächlich werden Gmail, HttpRequest, Agent, ChatTrigger, LmChatOpenAi und andere Nodes verwendet. Automatisierung der Podcast-Erstellung durch GPT, Claude und Eleven Labs Text-to-Speech

Voraussetzungen
  • Google-Konto + Gmail API-Anmeldedaten
  • Möglicherweise sind Ziel-API-Anmeldedaten erforderlich
  • OpenAI API Key
  • Anthropic 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
{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "Podcast on Autopilot",
  "tags": [],
  "nodes": [
    {
      "id": "b0c623b4-0277-4ded-b3e9-efa144b8dbab",
      "name": "Bei Chat-Nachricht empfangen",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -448,
        0
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.3
    },
    {
      "id": "e5411e46-4ffa-413b-8058-66b20bc4f2a6",
      "name": "OpenAI-Chat-Modell",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -144,
        192
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "YOUR_OPENAI_CREDENTIAL_ID",
          "name": "OpenAI Account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "9a92346c-c2ed-49cb-8852-146ebf1eb0a5",
      "name": "Simple Speicher",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        48,
        192
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "fd396cfc-befe-4ec1-86a6-628034521233",
      "name": "Anthropic-Chat-Modell",
      "type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
      "position": [
        336,
        192
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "claude-sonnet-4-20250514",
          "cachedResultName": "Claude 4 Sonnet"
        },
        "options": {}
      },
      "credentials": {
        "anthropicApi": {
          "id": "YOUR_ANTHROPIC_CREDENTIAL_ID",
          "name": "Anthropic Account"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "0545dea0-8429-4548-8cd5-9367223581d2",
      "name": "Simple Speicher1",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        496,
        192
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "83ea47ca-b58c-488c-8e5e-3d236e8b5766",
      "name": "Podcast Script Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        432,
        0
      ],
      "parameters": {
        "text": "={{ $json.output }}",
        "options": {
          "systemMessage": "=ROLE\n\nYou are a Podcast Script Writer for a solo monologue show. Write only the intro (≤ 60 seconds of spoken audio). The Script should sound as human-like natural as possible and in a \"your-everyday-friendly-neighbourhood-dude\" type of way. Tonality should be in the style of Joe Rogan and Steven Bartlett, engaging, relatable and keeps the listener engaged.\n\nINPUTS\n\nYou will receive Podcast topic and idea outline from user input\n\nGOAL\n\nTurn the title + idea into a natural, high-impact opening that grabs attention in the first 10 seconds, sets the premise, and cleanly hands off to the main segment.\n\nLENGTH & PACING\n\nTarget 135–160 words (≈ 50–60 seconds at normal speech).\n\nShort sentences. Conversational cadence. Use contractions.\n\nSTYLE (Rogan/Bartlett-inspired)\n\nCurious, grounded, reflective, practical.\n\nConfident but not preachy. No jargon.\n\nMonologue only (no guests, no interview framing).\n\nSTRUCTURE (use this flow, but do not label it)\n\nCold-open hook (a punchy line or provocative question).\n\nWhy now (timely tension or curiosity gap).\n\nPromise (what listeners will get by staying).\n\nTease 2–3 beats (surprising angle, personal reflection, actionable insight).\n\nSeamless handoff (\"Let's dive in.\" / \"Here's the play.\").\n\nLANGUAGE GUARDRAILS\n\nNo stage directions, no sound cues, no hashtags, no links, no emojis.\n\nAvoid brand/sponsor mentions, medical/financial/legal advice, hate/harassment, or unsafe claims.\n\nIf the idea references names, places, or numbers that require confirmation, generalize them (e.g., \"a leading researcher,\" \"a major study\")—do not use placeholders or brackets like [Name], write around them.\n\nOUTPUT RULES\n\nOutput only the script text.\n\nNo titles, labels, markup, JSON, or explanations.\n\nThe script must stand alone, **ready for text-to-speech**.\n\nEXAMPLE OPENING MOVES (in spirit, not to copy)\n\n\"What if the habit you're most proud of is quietly holding you back?\"\n\n\"Today, I want to test a belief most of us never question…\""
        },
        "promptType": "define"
      },
      "typeVersion": 2.2
    },
    {
      "id": "465f65c8-ee1c-47ff-9a28-006833e8080e",
      "name": "Podcast Idea/Topic Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        0,
        0
      ],
      "parameters": {
        "options": {
          "systemMessage": "=ROLE\n\nYou are a Podcast Idea Generator for a solo, monologue-style show. The vibe is fun, natural, and thought-provoking—in the spirit of Joe Rogan and Steven Bartlett (curious, reflective, practical)—but without guests or interviews. The topic should be relatable, buddy, down-to-earth-type of tonality.\n\nOBJECTIVE\n\nFrom a given seed topic, produce one compelling episode idea suitable for a monologue podcast.\n\nVOICE & AUDIENCE\n\nVoice: conversational, curious, balanced; no preachiness or jargon.\n\nAudience: smart general listeners who enjoy big ideas grounded in everyday life.\n\nCONTENT RULES\n\nPropose one clear, specific angle (not a broad theme).\n\nInclude a strong hook and a logical flow (setup → tension → insight → takeaway).\n\nAdd one surprising or contrarian twist to keep it thought-provoking.\n\nKeep it actionable: end with 1–2 practical reflections or experiments for listeners.\n\nAvoid medical/financial/legal advice; no hate or unsafe content.\n\nOUTPUT FORMAT (JSON, SINGLE STRING OBJECT)\n\nReturn only valid JSON with exactly one field, where the value is the full idea (hook + angle + flow + takeaway) as a single string. No lists, no extra fields, no commentary."
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "2584ac19-dc78-4837-adc8-ac391467890d",
      "name": "Send a message",
      "type": "n8n-nodes-base.gmail",
      "position": [
        1168,
        0
      ],
      "parameters": {
        "sendTo": "your-email@example.com",
        "message": "Podcast Audio File",
        "options": {
          "attachmentsUi": {
            "attachmentsBinary": [
              {}
            ]
          }
        },
        "subject": "Podcast Audio File"
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "YOUR_GMAIL_CREDENTIAL_ID",
          "name": "Gmail Account"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "aa1eb4df-6746-4411-8e6d-ad06929e1fbf",
      "name": "Eleven Labs Text-to-Speech",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        880,
        0
      ],
      "parameters": {
        "url": "https://api.elevenlabs.io/v1/text-to-speech/YOUR_VOICE_ID",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "sendQuery": true,
        "sendHeaders": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "text",
              "value": "={{ $json.output }}"
            },
            {
              "name": "model_id",
              "value": "eleven_multilingual_v2"
            }
          ]
        },
        "queryParameters": {
          "parameters": [
            {
              "name": "output_format",
              "value": "mp3_44100_128"
            }
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "xi-api-key",
              "value": "YOUR_ELEVENLABS_API_KEY"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "fc779931-a9b2-47d5-a214-790c1ae4a5d2",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -576,
        -272
      ],
      "parameters": {
        "width": 384,
        "height": 784,
        "content": "Chat Trigger Message"
      },
      "typeVersion": 1
    },
    {
      "id": "33a14b8d-73b0-4302-bb55-901af7c1a371",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -176,
        -272
      ],
      "parameters": {
        "color": 5,
        "width": 464,
        "height": 784,
        "content": "Podcast Idea Generator Agent"
      },
      "typeVersion": 1
    },
    {
      "id": "52778ddd-589f-4e72-b523-e956219999ac",
      "name": "Haftnotiz2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        304,
        -272
      ],
      "parameters": {
        "color": 4,
        "width": 464,
        "height": 784,
        "content": "Podcast Script Generator"
      },
      "typeVersion": 1
    },
    {
      "id": "a5562271-12cb-4e3e-9a1e-415b00848010",
      "name": "Haftnotiz3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        784,
        -272
      ],
      "parameters": {
        "color": 3,
        "width": 304,
        "height": 784,
        "content": "Eleven Labs POST Request"
      },
      "typeVersion": 1
    },
    {
      "id": "35f00176-86b3-4803-a29e-adebc5eb27c6",
      "name": "Haftnotiz4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1104,
        -272
      ],
      "parameters": {
        "color": 7,
        "width": 304,
        "height": 784,
        "content": "Send Audio File to Email"
      },
      "typeVersion": 1
    },
    {
      "id": "1ce57aeb-ca5f-49a3-bc8f-c754ba9367b8",
      "name": "Haftnotiz5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1440,
        -640
      ],
      "parameters": {
        "width": 592,
        "height": 304,
        "content": "@[youtube](Dan3_W1JoqU)"
      },
      "typeVersion": 1
    },
    {
      "id": "c450891b-9582-4000-9bbe-2fa1469309cd",
      "name": "Haftnotiz6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1440,
        -288
      ],
      "parameters": {
        "width": 816,
        "height": 816,
        "content": "Podcast on Autopilot — Generate Podcast Ideas, Scripts & Audio Automatically\n\nBring your solo podcast to life — on full autopilot. This workflow uses GPT-4 and Claude Sonnet to turn a single topic input into a complete podcast episode intro and ready-to-send audio file.\n\nHow it works\n\nStart a chat trigger — enter a seed idea or topic (e.g., \"habits,\" \"failure,\" \"technology and purpose\").\n\nPodcast Idea Agent (GPT-4) instantly crafts a thought-provoking, Rogan- or Bartlett-style episode concept with a clear angle and takeaway.\n\nPodcast Script Agent (Claude 4 Sonnet) expands that idea into a natural, engaging 60-second opening monologue ready for recording.\n\nText-to-Speech via ElevenLabs automatically converts the script into a high-quality voice track.\n\nEmail automation sends the finished MP3 directly to your inbox.\n\nPerfect for\n• Solo creators who want to ideate, script and voice short podcasts effortlessly\n• Content teams prototyping daily or weekly audio snippets\n• Anyone testing AI-driven storytelling pipelines\n\n\nCustomization tips\n• Swap ElevenLabs with your preferred TTS service by editing the HTTP Request node.\n• Adjust prompt styles for tone or audience in the Idea and Script Agents.\n• Modify the Gmail (or other mail service) node to send audio to any destination (Drive, Slack, Notion, etc.).\n• For reuse at scale, add variables for episode number, guest name, or theme category — just clone and update the trigger node.\n\nWatch step-by-step tutorial (how to build it yourself)\nhttps://www.youtube.com/watch?v=Dan3_W1JoqU\n\nRequirements & disclaimer\n• Requires API keys for OpenAI + Anthropic + ElevenLabs (or your chosen TTS).\n• You're responsible for managing costs incurred through AI or TTS usage.\n• Avoid sharing sensitive or private data as input into prompt flows.\n• Designed with modularity so you can turn off or swap/deep-link any stage (idea → script → voice → email) without breaking the chain."
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "connections": {
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "465f65c8-ee1c-47ff-9a28-006833e8080e",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory1": {
      "ai_memory": [
        [
          {
            "node": "83ea47ca-b58c-488c-8e5e-3d236e8b5766",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "465f65c8-ee1c-47ff-9a28-006833e8080e",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Anthropic Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "83ea47ca-b58c-488c-8e5e-3d236e8b5766",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "83ea47ca-b58c-488c-8e5e-3d236e8b5766": {
      "main": [
        [
          {
            "node": "aa1eb4df-6746-4411-8e6d-ad06929e1fbf",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "465f65c8-ee1c-47ff-9a28-006833e8080e": {
      "main": [
        [
          {
            "node": "83ea47ca-b58c-488c-8e5e-3d236e8b5766",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "aa1eb4df-6746-4411-8e6d-ad06929e1fbf": {
      "main": [
        [
          {
            "node": "2584ac19-dc78-4837-adc8-ac391467890d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "465f65c8-ee1c-47ff-9a28-006833e8080e",
            "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?

Experte - Content-Erstellung, Multimodales KI

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
Experte
Anzahl der Nodes16
Kategorie2
Node-Typen8
Schwierigkeitsbeschreibung

Für fortgeschrittene Benutzer, komplexe Workflows mit 16+ Nodes

Autor
Automate With Marc

Automate With Marc

@marconi

Automating Start-Up and Business processes. Helping non-techies understand and leverage Agentic AI with easy to understand step-by-step tutorials. Check out my educational content: https://www.youtube.com/@Automatewithmarc

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34