This workflow follows the Chainllm → HTTP Request 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 →
{
"name": "InsightsLM - Podcast Generation",
"nodes": [
{
"parameters": {
"command": "if ffmpeg -version > /dev/null 2>&1; then\n echo \"FFmpeg is installed\"\nelse\n echo \"FFmpeg is NOT installed\"\nfi\n"
},
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
-420,
1320
],
"id": "b804e4c1-5f49-4fb6-943b-92f183c302a9",
"name": "Check is FFMPEG Installed"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "05ef5c0e-fe71-4367-a88d-6ba65b8e4e48",
"leftValue": "={{ $json.stdout }}",
"rightValue": "=FFmpeg is installed",
"operator": {
"type": "string",
"operation": "equals"
}
},
{
"id": "3e8219ed-4cfb-4706-b6c0-6cdf4e1d1c3b",
"leftValue": "",
"rightValue": "",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
-200,
1320
],
"id": "3adf9104-7091-4b88-b45b-efdb219c7742",
"name": "If"
},
{
"parameters": {
"respondWith": "json",
"responseBody": "{\n \"message\": \"Workflow was started\"\n}",
"options": {
"responseCode": 200
}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.4,
"position": [
100,
1200
],
"id": "54c2c7a8-af45-488e-9439-997d43ca2676",
"name": "Respond to Webhook"
},
{
"parameters": {
"respondWith": "json",
"responseBody": "{\n \"error\": \"FFmpeg not installed\",\n \"code\": \"FFMPEG_NOT_INSTALLED\",\n \"details\": \"The server requires ffmpeg to be installed\"\n}",
"options": {
"responseCode": 500
}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.4,
"position": [
100,
1380
],
"id": "2b492335-fad2-4981-8c5c-bd790256bddd",
"name": "Respond with 500 Error"
},
{
"parameters": {
"content": "## To Do \n- REQUIREMENT: FFMPEG needs to be installed on your server for this workflow to succeed\n- Configure the Supabase nodes to reference your Project\n- Configure your Google Cloud API credentials\n- Update the Host of the \"HTTP Requests\" to hit your project",
"width": 680,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2040,
840
],
"id": "73fb9911-4a7c-413b-8bb9-9ec86a3f501e",
"name": "Sticky Note1"
},
{
"parameters": {
"httpMethod": "POST",
"path": "4c4699bc-004b-4ca3-8923-373ddd4a274e",
"authentication": "headerAuth",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
-680,
1320
],
"id": "36040655-7e2a-4af2-8524-f0e84fa2c874",
"name": "Webhook",
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "getAll",
"tableId": "sources",
"returnAll": true,
"filters": {
"conditions": [
{
"keyName": "notebook_id",
"condition": "eq",
"keyValue": "={{ $('Webhook').item.json.body.notebook_id }}"
}
]
}
},
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
360,
1200
],
"id": "2bf3e04b-7472-4a31-80e3-c78fb8f742be",
"name": "Get Sources",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"aggregate": "aggregateAllItemData",
"include": "specifiedFields",
"fieldsToInclude": "title,content",
"options": {}
},
"type": "n8n-nodes-base.aggregate",
"typeVersion": 1,
"position": [
580,
1200
],
"id": "30a71143-107d-4c02-a43f-54d972c42437",
"name": "Aggregate"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "c3743cbc-c838-401a-8f65-95a386707ded",
"name": "prompt",
"value": "=I\u2019ll give you the text of SOURCE(S) and I\u2019d like you to use the instructions below to write a podcast script\n\n# EXAMPLE OUTPUT STRUCTURE & TRANSCRIPT\n\nPlease read aloud the following in a podcast interview style:\nSpeaker 1: When you watch a Formula One car flash by, it's just an incredible sight. \nSpeaker 2: These things are absolute apex predators of engineering, aren't they? Machines designed purely for speed, pushing everything, materials, aero to the absolute limit. Every single part feels like a technological marvel. It really does.\nSpeaker 1: And what's amazing is that these cars, they weren't just dreamt up in a vacuum. You know, they actually exist within this incredibly tight box, a really, really detailed rulebook that dictates pretty much everything that is and isn't possible.\nSpeaker 2: Exactly. And for this deep dive, we're going straight to the source of that box. Our material today is key sections from the official 2025 Formula One technical regulations put out by the sports governing body, the FIA. Yeah. And our mission here for you listening is really to kind of pull back the curtain on that rulebook. We want to unpack these regulations, try and understand the fundamental principles, maybe some of the surprising details, and just grasp how much complexity is actually baked into the blueprint of an F1 car. It's not just, you know, dry rules. It's the framework that shapes performance, safety and that constant, fascinating battle of innovation we see season after season.\nSpeaker 1: OK, so let's start right at the top then. Yeah. The regulations make it pretty clear who's running the show. It's the FIA, right? They own and organize the Formula One World Championship. They're the ones handing out those coveted titles for drivers, constructors.\nSpeaker 2: That's right. And beneath that sort of top level, there are layers upon layers of rules governing absolutely everything. The championship itself, every single competition within it. So each race weekend, they're governed by the International Sporting Code. These technical regulations we're looking at today, the sporting regulations which cover race procedures, penalties, that kind of thing.\n\n# INSTRUCTIONS TO FOLLOW\n\n1. Opening:\n\u2013 Begin with some interesting opening remarks on the topic between the hosts\n\u2013 Then introduce the topic as a \u201cdeep dive\u201d into the subject matter.\n\n2. Dialog Structure:\n\u2013 Use two hosts who engage in a conversational back-and-forth.\n\u2013 Alternate between short, punchy statements and longer explanations.\n\u2013 Use frequent affirmations like \u201cRight,\u201d \u201cExactly,\u201d and \u201cAbsolutely\u201d to maintain flow and agreement.\n\n3. Language and Tone:\n\u2013 Keep the language informal and accessible. Use contractions and colloquialisms.\n\u2013 Maintain an enthusiastic, energetic tone throughout.\n\u2013 Use rhetorical questions to transition between points: \u201cIt\u2019s fascinating, isn\u2019t it?\u201d\n\u2013 Employ phrases like \u201cYou know\u201d and \u201cI mean\u201d to maintain a casual feel.\n\n4. Content Presentation:\n\u2013 Introduce source material (e.g., articles, studies) early in the discussion.\n\u2013 Use analogies to explain complex concepts: \u201cIt\u2019s like\u2026\u201d\n\u2013 Break down ideas into digestible chunks, often using numbered points or clear transitions.\n\n5. Interaction Between Hosts:\n\u2013 Have one host pose questions or express confusion, allowing the other to explain.\n\u2013 Use phrases like \u201cYou\u2019ve hit the nail on the head\u201d to validate each other\u2019s points.\n\u2013 Build on each other\u2019s ideas, creating a collaborative feel.\n\n6. Engagement Techniques:\n\u2013 Address the audience directly at times: \u201cSo to everyone listening\u2026\u201d\n\u2013 Pose thought-provoking questions for the audience to consider.\n\n7. Structure and Pacing:\n\u2013 Start with a broad introduction of the topic and narrow down to specific points.\n\u2013 Use phrases like \u201cSo we\u2019ve established\u2026\u201d to summarize and move to new points.\n\u2013 Maintain a brisk pace, but allow for moments of reflection on bigger ideas.\n\n8. Concluding the Episode:\n\u2013 Signal the wrap-up with \u201cSo as we wrap things up\u2026\u201d\n\u2013 Pose a final thought-provoking question or takeaway.\n\u2013 Use the phrase \u201cAnd on that note\u2026\u201d to transition to the closing.\n\u2013 Encourage continued engagement: \u201cstay curious, keep those questions coming.\u201d\n\u2013 End with a consistent sign-off: \u201cUntil next time, keep [relevant verb].\u201d\n\n9. Overall Flow:\n\u2013 Begin with the misconception or general understanding of the topic.\n\u2013 Introduce expert sources that challenge or deepen this understanding.\n\u2013 Discuss implications and broader context of the new information.\n\u2013 Conclude with how this knowledge affects the listener or the field at large.\n\nRemember to maintain a balance between informative content and engaging conversation, always keeping the tone friendly and accessible regardless of the complexity of the topic.\n\n# SOURCE(S) TO CREATE TRANSCRIPT FROM\n\n{{ JSON.stringify($json.data) }}\n\n# OTHER\n\nIMPORTANT: Only output the transcript and use \\n in between speakers dialog\nIMPORTANT: Your response must start with ...\n\"Please read aloud the following in a podcast interview style:\nSpeaker 1: \"",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
840,
1200
],
"id": "a12a3968-6929-489f-a497-a837f3c7e13c",
"name": "Set Prompt"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.prompt }}",
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.7,
"position": [
1100,
1180
],
"id": "25ae0627-f92b-4fa3-8722-6ce6cb678697",
"name": "Basic LLM Chain",
"retryOnFail": true,
"waitBetweenTries": 5000,
"maxTries": 5
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-4.1",
"mode": "list",
"cachedResultName": "gpt-4.1"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
1100,
1400
],
"id": "a805fc31-c265-49cc-8a95-e79ec7311783",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview-tts:generateContent",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "googlePalmApi",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"contents\": [{\n \"parts\":[{\n \"text\": {{ JSON.stringify($json.text) }}\n }]\n }],\n \"generationConfig\": {\n \"responseModalities\": [\"AUDIO\"],\n \"speechConfig\": {\n \"multiSpeakerVoiceConfig\": {\n \"speakerVoiceConfigs\": [{\n \"speaker\": \"Joe\",\n \"voiceConfig\": {\n \"prebuiltVoiceConfig\": {\n \"voiceName\": \"Algenib\"\n }\n }\n }, {\n \"speaker\": \"Jane\",\n \"voiceConfig\": {\n \"prebuiltVoiceConfig\": {\n \"voiceName\": \"Kore\"\n }\n }\n }]\n }\n }\n },\n \"model\": \"gemini-2.5-flash-preview-tts\"\n}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1520,
1180
],
"id": "acf52aa8-77ad-41ba-8b27-66f496be6454",
"name": "Generate Audio",
"retryOnFail": true,
"waitBetweenTries": 5000,
"maxTries": 5,
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "toBinary",
"sourceProperty": "candidates[0].content.parts[0].inlineData.data",
"options": {
"fileName": "audio.pcm",
"mimeType": "audio/L16"
}
},
"type": "n8n-nodes-base.convertToFile",
"typeVersion": 1.1,
"position": [
1740,
1180
],
"id": "0c297369-7ff9-45f8-be19-83191b69a676",
"name": "Convert to File"
},
{
"parameters": {
"operation": "write",
"fileName": "=/tmp/{{ $('Generate Audio').item.json.responseId }}-in.pcm",
"options": {}
},
"type": "n8n-nodes-base.readWriteFile",
"typeVersion": 1,
"position": [
1960,
1180
],
"id": "d6a89506-9cd2-4486-85a1-be20060d5d04",
"name": "Read/Write Files from Disk"
},
{
"parameters": {
"command": "=ffmpeg -f s16le -ar 24000 -ac 1 -i /tmp/{{ $('Generate Audio').item.json.responseId }}-in.pcm -codec:a libmp3lame -qscale:a 2 /tmp/{{ $('Generate Audio').item.json.responseId }}-out.mp3"
},
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
2200,
1180
],
"id": "d3f96ec9-2373-4ca7-8282-c078de61b92b",
"name": "Execute Command"
},
{
"parameters": {
"fileSelector": "=/tmp/{{ $('Generate Audio').item.json.responseId }}-out.mp3",
"options": {}
},
"type": "n8n-nodes-base.readWriteFile",
"typeVersion": 1,
"position": [
2420,
1180
],
"id": "5d91d055-300e-4a33-b3e9-fac3b25dd3e0",
"name": "Read/Write Files from Disk1"
},
{
"parameters": {
"method": "POST",
"url": "=https://yfvmutoxmibqzvyklggr.supabase.co/storage/v1/object/audio/{{ $('Webhook').item.json.body.notebook_id}}/{{ $binary.data.fileName }}",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "supabaseApi",
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"parameterType": "formBinaryData",
"name": "file",
"inputDataFieldName": "data"
}
]
},
"options": {
"response": {
"response": {
"fullResponse": true
}
}
}
},
"id": "65a6bb6c-99e1-4e17-ac97-95bf0e23a954",
"name": "Upload object",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.1,
"position": [
2640,
1180
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "=https://yfvmutoxmibqzvyklggr.supabase.co/storage/v1/object/sign/{{ $json.body.Key }}",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "supabaseApi",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"expiresIn\": 86400\n}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2840,
1180
],
"id": "f05a5230-c0c5-4b55-b50c-57b1a3c4df83",
"name": "Generate Signed URL",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Loop over input items and add a new field called 'myNewField' to the JSON of each one\nfor (const item of $input.all()) {\n const now = new Date();\n const tomorrow = new Date(now.getTime() + 24 * 60 * 60 * 1000); // Add 1 day in ms\n item.json.timestamp = tomorrow.toISOString(); // Compatible with Supabase timestampz\n}\n\nreturn $input.all();\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
3080,
1180
],
"id": "8d5764b9-498a-4a73-a62a-69ccb6fa5716",
"name": "Generate Timestamp for Expires"
},
{
"parameters": {
"operation": "update",
"tableId": "notebooks",
"filters": {
"conditions": [
{
"keyName": "id",
"condition": "eq",
"keyValue": "={{ $('Webhook').item.json.body.notebook_id }}"
}
]
},
"fieldsUi": {
"fieldValues": [
{
"fieldId": "audio_overview_url",
"fieldValue": "=https://yfvmutoxmibqzvyklggr.supabase.co/storage/v1/{{ $json.signedURL }}"
},
{
"fieldId": "audio_url_expires_at",
"fieldValue": "={{ $json.timestamp }}"
},
{
"fieldId": "audio_overview_generation_status",
"fieldValue": "completed"
}
]
}
},
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
3340,
1180
],
"id": "e549327c-f98e-4119-82b0-92c8e902fd06",
"name": "Supabase",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "[](https://www.theaiautomators.com/)\n## InsightsLM\nhttps://github.com/theaiautomators/insights-lm-public",
"height": 220,
"width": 280,
"color": 7
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-680,
900
],
"id": "f1d8ead0-76e7-4a47-8399-969861b08a46",
"name": "Sticky Note8"
}
],
"connections": {
"Check is FFMPEG Installed": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"If": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
],
[
{
"node": "Respond with 500 Error",
"type": "main",
"index": 0
}
]
]
},
"Respond to Webhook": {
"main": [
[
{
"node": "Get Sources",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Check is FFMPEG Installed",
"type": "main",
"index": 0
}
]
]
},
"Get Sources": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Set Prompt",
"type": "main",
"index": 0
}
]
]
},
"Set Prompt": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Generate Audio",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Generate Audio": {
"main": [
[
{
"node": "Convert to File",
"type": "main",
"index": 0
}
]
]
},
"Convert to File": {
"main": [
[
{
"node": "Read/Write Files from Disk",
"type": "main",
"index": 0
}
]
]
},
"Read/Write Files from Disk": {
"main": [
[
{
"node": "Execute Command",
"type": "main",
"index": 0
}
]
]
},
"Execute Command": {
"main": [
[
{
"node": "Read/Write Files from Disk1",
"type": "main",
"index": 0
}
]
]
},
"Read/Write Files from Disk1": {
"main": [
[
{
"node": "Upload object",
"type": "main",
"index": 0
}
]
]
},
"Upload object": {
"main": [
[
{
"node": "Generate Signed URL",
"type": "main",
"index": 0
}
]
]
},
"Generate Signed URL": {
"main": [
[
{
"node": "Generate Timestamp for Expires",
"type": "main",
"index": 0
}
]
]
},
"Generate Timestamp for Expires": {
"main": [
[
{
"node": "Supabase",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "f228bda4-191c-47b3-a8b0-e8e16d374eb5",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "bxrCsRKl157B5Lyt",
"tags": [
{
"createdAt": "2025-05-12T13:43:59.783Z",
"updatedAt": "2025-05-12T13:43:59.783Z",
"id": "d3ygIhrGjDmzgrW0",
"name": "TheAIAutomators.com"
}
]
}
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.
googlePalmApihttpHeaderAuthopenAiApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
InsightsLM - Podcast Generation. Uses executeCommand, supabase, chainLlm, lmChatOpenAi. Webhook trigger; 21 nodes.
Source: https://github.com/arnikanord/Notebook-LM-clone/blob/main/n8n/InsightsLM___Podcast_Generation.json — 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.
leads. Uses supabase, gmail, formTrigger, httpRequest. Webhook trigger; 62 nodes.
Supabase, Gmail, Form Trigger +13
Docsify example. Uses convertToFile, extractFromFile, html, sort. Webhook trigger; 60 nodes.
Read Write File, n8n, Chain Llm +4
This workflow creates a documentation system for n8n instances using Docsify.js. It serves a dynamic documentation website that allows users to: View an overview of all workflows in a tabular format F
Read Write File, n8n, Chain Llm +4
Docsify example. Uses readWriteFile, n8n, chainLlm, lmChatOpenAi. Webhook trigger; 60 nodes.
Read Write File, n8n, Chain Llm +4
Content Creator. Uses lmChatOpenAi, httpRequest, supabase, outputParserStructured. Webhook trigger; 22 nodes.
OpenAI Chat, HTTP Request, Supabase +3