Friedemann Schuetz This workflow corresponds to n8n.io template #4496 — we link there as the canonical source.
This workflow follows the Agent → Anthropic Chat recipe pattern — see all workflows that pair these two integrations.
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 →
{
"id": "zCH7mVwHTPMedQnn",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Wikipedia Podcast Telegram Agent - Template",
"tags": [],
"nodes": [
{
"id": "02ec8740-62ea-4803-aec0-93ec18f24be1",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-1000,
-80
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "0820738d-45f2-49fe-8837-bd9fdbde5a25",
"name": "Anthropic Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
-120,
140
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-20250514",
"cachedResultName": "Claude 4 Sonnet"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "665f8751-48b8-46cc-bd76-d82127435ea2",
"name": "Wikipedia",
"type": "@n8n/n8n-nodes-langchain.toolWikipedia",
"position": [
0,
140
],
"parameters": {},
"typeVersion": 1
},
{
"id": "54b0a604-9e7c-43dc-899b-80432e1e9aa8",
"name": "Think",
"type": "@n8n/n8n-nodes-langchain.toolThink",
"position": [
120,
140
],
"parameters": {},
"typeVersion": 1
},
{
"id": "8c4ecbd4-e340-4017-9c73-eea76aecb30f",
"name": "Text or Voice",
"type": "n8n-nodes-base.switch",
"position": [
-780,
-80
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "7c629699-9dd6-4a75-9b76-d796875f9ac9",
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
},
"leftValue": "={{ $json.message.text }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Voice",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "0e56bc7f-c754-4f5e-9ddd-7124e1f5d998",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.voice }}",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "4a62e7d8-204d-407e-a090-3dcad37c70b2",
"name": "Get Voice Message",
"type": "n8n-nodes-base.telegram",
"position": [
-560,
20
],
"parameters": {
"fileId": "={{ $json.message.voice.file_id }}",
"resource": "file"
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "7c0a4950-13c5-401a-b9bc-3409cd8cde24",
"name": "Transcribe Voice Message",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-340,
20
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "transcribe"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.8
},
{
"id": "73daa7c9-124f-4595-ae2a-de4aa9ce1cd4",
"name": "Prepare Text Message for AI Agent",
"type": "n8n-nodes-base.set",
"position": [
-340,
-180
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "a5bcf087-7580-4904-88d3-ca29614fc923",
"name": "text",
"type": "string",
"value": "={{ $json.message.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "c8d4fa95-94b4-47ae-9332-4cefe844d4f0",
"name": "ElevenLabs Text to Speech",
"type": "@elevenlabs/n8n-nodes-elevenlabs.elevenLabs",
"position": [
320,
-80
],
"parameters": {
"text": "={{ $json.output }}",
"voice": {
"__rl": true,
"mode": "list",
"value": "yUy9CCX9brt8aPVvIWy3",
"cachedResultName": "Ramona - Calm & Soothing Voice"
},
"resource": "speech",
"requestOptions": {},
"additionalOptions": {}
},
"credentials": {
"elevenLabsApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "119ec323-c887-45ac-bd9d-b1b7691789df",
"name": "Send Voice Response",
"type": "n8n-nodes-base.telegram",
"position": [
540,
-80
],
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"operation": "sendAudio",
"binaryData": true,
"additionalFields": {
"caption": "=\ud83c\udf99\ufe0f Wikipedia-Podcast: {{ $('Telegram Trigger').item.json.message.text }}",
"fileName": "={{ $('Telegram Trigger').item.json.message.text }}.mp3"
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "c2e46d2f-01e9-4512-b44d-5b2bae881341",
"name": "Wikipedia Podcast Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-88,
-80
],
"parameters": {
"text": "={{ $json.text }}",
"options": {
"systemMessage": "=You are a professional podcast host who creates captivating and informative 5-minute podcasts about Wikipedia articles. Your task is to produce an engaging, well-structured podcast from the topic mentioned by the user.\n\n## Your Working Method:\n\n1. **Research**: Use the Wikipedia tool to gather comprehensive information about the desired topic\n2. **Deep Dive**: Search for additional interesting details, backgrounds, and connections\n3. **Podcast Creation**: Create approximately a 5-minute podcast text (about 600-750 words)\n\n## Podcast Structure:\n\n**Intro (30-45 seconds)**\n- Greet the listeners warmly\n- Introduce the topic and spark curiosity\n- Give a brief preview of the most interesting aspects\n\n**Main Part (3.5-4 minutes)**\n- Tell the story chronologically or thematically structured\n- Emphasize particularly fascinating, surprising, or little-known facts\n- Use vivid descriptions and concrete examples\n- Make connections to current events or other well-known topics\n\n**Outro (30-45 seconds)**\n- Summarize the most important insights\n- Encourage reflection or pose an interesting concluding question\n- Say goodbye in a friendly manner\n\n## Style Guidelines:\n\n- **Conversational**: Speak as if you were telling a fascinating story to a friend\n- **Accessible**: Explain complex matters understandably without oversimplifying\n- **Enthusiastic**: Show your enthusiasm for the topic\n- **Structured**: Use clear transitions between sections\n- **Lively**: Use rhetorical questions, short pauses (marked with \"...\") and vary the pace\n- **Direct**: Continuously address the listeners with \"you\" - they are your conversation partners\n- **Tangible**: Translate large numbers and abstract statistics into understandable comparisons\n\n## Special Notes:\n\n- Pay attention to natural language suitable for speaking\n- Avoid overly long sentences or complicated nested clauses\n- Occasionally integrate \"By the way...\" or \"Did you know that...\" for additional facts\n- **No stage directions**: NEVER use brackets with music or sound cues like [INTRO MUSIC] or [OUTRO MUSIC]\n- **Make numbers tangible**: Translate large statistics into comparisons (e.g., \"As many people as live in all of Bavaria today\" instead of \"13 million\")\n- **Continuous listener address**: Use \"you\" throughout - the listeners are always directly addressed\n- Always ensure that all information comes from reliable Wikipedia sources\n\nNow create a captivating podcast about the desired topic!"
},
"promptType": "define"
},
"typeVersion": 2
},
{
"id": "d6dc5f36-789e-46df-88cd-2ad9b0be7d59",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1900,
-540
],
"parameters": {
"width": 820,
"height": 1140,
"content": "# Welcome to my Wikipedia Podcast Telegram Agent Workflow!\n\n## This workflow has the following sequence:\n\n1. **Telegram Trigger** - Receives incoming messages (text or voice) from users via Telegram bot\n2. **Text or Voice Switch** - Routes the message based on input type (text message vs. voice message)\n3. **Voice Message Processing** (if voice input):\n - Retrieval of voice file from Telegram\n - Transcription of voice message to text using OpenAI Whisper\n4. **Text Message Preparation** (if text input) - Prepares the text message for the AI agent\n5. **Wikipedia Podcast Agent** - Core AI agent that:\n - Researches the requested topic using Wikipedia tool\n - Creates a professional 5-minute podcast script (600-750 words)\n - Follows structured format: intro, main content, outro\n - Uses conversational, accessible, and enthusiastic tone\n6. **ElevenLabs Text to Speech** - Converts the podcast script into natural-sounding audio using AI voice synthesis\n7. **Send Voice Response** - Delivers the generated podcast audio back to the user via Telegram\n\n## The following accesses are required for the workflow:\n\n- **Telegram Bot API**: [Documentation](https://docs.n8n.io/integrations/builtin/credentials/telegram/)\n- **Anthropic API** (Claude 4 Sonnet): [Documentation](https://docs.n8n.io/integrations/builtin/credentials/anthropic/)\n- **OpenAI API** (for voice transcription): [Documentation](https://docs.n8n.io/integrations/builtin/credentials/openai/)\n- **ElevenLabs API** (for text-to-speech): [Documentation](https://github.com/n8n-ninja/n8n-nodes-elevenlabs?tab=readme-ov-fil/)\n\n## Workflow Features:\n\n- **Multi-input support**: Accepts both text and voice messages from Telegram users\n- **Wikipedia integration**: Automatically researches topics using Wikipedia data\n- **Professional podcast generation**: Creates structured, engaging 5-minute podcast episodes\n- **Natural voice synthesis**: Converts text to high-quality speech using AI\n- **Seamless user experience**: Users receive audio responses directly in Telegram chat\n\n## Use Cases:\n\n- Educational content creation\n- Quick Wikipedia topic summaries in podcast format\n- Accessibility tool for consuming Wikipedia content\n- Personal learning assistant\n- Content creation for social media or educational purposes\n\nYou can contact me via LinkedIn, if you have any questions: https://www.linkedin.com/in/friedemann-schuetzt "
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "5355ca40-6418-40b0-9b54-2add30a8bb1e",
"connections": {
"Think": {
"ai_tool": [
[
{
"node": "Wikipedia Podcast Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Wikipedia": {
"ai_tool": [
[
{
"node": "Wikipedia Podcast Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Text or Voice": {
"main": [
[
{
"node": "Prepare Text Message for AI Agent",
"type": "main",
"index": 0
}
],
[
{
"node": "Get Voice Message",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Text or Voice",
"type": "main",
"index": 0
}
]
]
},
"Get Voice Message": {
"main": [
[
{
"node": "Transcribe Voice Message",
"type": "main",
"index": 0
}
]
]
},
"Anthropic Chat Model": {
"ai_languageModel": [
[
{
"node": "Wikipedia Podcast Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Wikipedia Podcast Agent": {
"main": [
[
{
"node": "ElevenLabs Text to Speech",
"type": "main",
"index": 0
}
]
]
},
"Transcribe Voice Message": {
"main": [
[
{
"node": "Wikipedia Podcast Agent",
"type": "main",
"index": 0
}
]
]
},
"ElevenLabs Text to Speech": {
"main": [
[
{
"node": "Send Voice Response",
"type": "main",
"index": 0
}
]
]
},
"Prepare Text Message for AI Agent": {
"main": [
[
{
"node": "Wikipedia Podcast Agent",
"type": "main",
"index": 0
}
]
]
}
}
}
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.
anthropicApielevenLabsApiopenAiApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n workflow template uses community nodes and is only compatible with the self-hosted version of n8n.
Source: https://n8n.io/workflows/4496/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Generate AI viral videos with NanoBanana & VEO3, shared on socials via Blotato 2. Uses @blotato/n8n-nodes-blotato, googleSheets, lmChatOpenAi, toolThink. Event-driven trigger; 94 nodes.
@Blotato/N8N Nodes Blotato, Google Sheets, OpenAI Chat +9
Jarvis is a powerful multi-agent productivity assistant built in n8n. It works directly from Telegram and can understand both text messages and voice notes.
Telegram Trigger, Telegram, OpenAI +10
This template is designed for marketers, content creators, and e-commerce brands who want to automate the creation of professional ad videos at scale. It’s ideal for teams looking to generate consiste
Telegram, Telegram Trigger, Google Drive +8
Template Carnaval - time instagram. Uses toolWorkflow, lmChatOpenAi, memoryBufferWindow, agent. Event-driven trigger; 56 nodes.
Tool Workflow, OpenAI Chat, Memory Buffer Window +10
This template is designed for anyone who wants to use Telegram as a personal AI assistant hub. If you often juggle tasks, emails, calendars, and expenses across multiple tools, this workflow consolida
OpenAI Chat, Memory Buffer Window, Mcp Client Tool +11