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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "f2ec712a-5120-44d8-9581-285d8b866322",
"name": "When clicking \"Execute Workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-160,
320
],
"parameters": {},
"typeVersion": 1
},
{
"id": "b16a56a5-0b0c-43cc-952c-f6db1b63d1e9",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
20,
60
],
"parameters": {
"color": 7,
"width": 199.37543798209555,
"height": 420.623805972039,
"content": "1] In ElevenLabs, add a voice to your [voice lab](https://elevenlabs.io/voice-lab) and copy its ID. Open this node and add the ID there"
},
"typeVersion": 1
},
{
"id": "08e26051-58e9-42c5-b198-7854ab3e58d6",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
240,
60
],
"parameters": {
"color": 7,
"width": 212,
"height": 418,
"content": "2] Get your ElevenLabs API key (click your name in the bottom-left of [ElevenLabs](https://elevenlabs.io/voice-lab) and choose \u2018profile\u2019)\n\nIn this node, create a new header auth cred. Set the name to `xi-api-key` and the value to your API key"
},
"typeVersion": 1
},
{
"id": "de6eb950-862e-472b-8776-b45e3109561a",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
60
],
"parameters": {
"color": 7,
"width": 392,
"height": 415,
"content": "3] In the 'credential' field of this node, create a new OpenAI cred with your [OpenAI API key](https://platform.openai.com/api-keys)"
},
"typeVersion": 1
},
{
"id": "e1d8158a-ad82-4b65-a2a8-a8f86cafd970",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-280,
20
],
"parameters": {
"color": 7,
"width": 230.39134868652621,
"height": 233.3354221029769,
"content": "### About\nThis workflow takes some French text, and translates it into spoken audio.\n\nIt then transcribes that audio back into text, translates it into English and generates an audio file of the English text"
},
"typeVersion": 1
},
{
"id": "9614bb02-3b9c-4c5d-b596-8f94704cdb8b",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
0
],
"parameters": {
"color": 7,
"width": 906,
"height": 498,
"content": "### Setup steps"
},
"typeVersion": 1
},
{
"id": "69ebcaf8-58ab-48ba-967a-a1f0497524bb",
"name": "Transcribe audio",
"type": "n8n-nodes-base.httpRequest",
"position": [
720,
320
],
"parameters": {
"url": "https://api.openai.com/v1/audio/transcriptions",
"method": "POST",
"options": {
"lowercaseHeaders": false
},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"authentication": "predefinedCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
},
{
"name": "model",
"value": "whisper-1"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "multipart/form-data"
}
]
},
"nodeCredentialType": "openAiApi"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "4109bccb-2bfd-454b-accb-074bd6980897",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
940,
500
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "5178a17e-737c-4ad1-8f56-95707430e892",
"name": "Set ElevenLabs voice ID and text",
"type": "n8n-nodes-base.set",
"position": [
60,
320
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "c0f610ff-e200-4e55-a140-e8a4d6fa0eed",
"name": "voice_id",
"type": "string",
"value": "Xb7hH8MSUJpSbSDYk0k2"
},
{
"id": "6755d8ae-e3df-465c-97ef-4f0187c31824",
"name": "text",
"type": "string",
"value": "=Apr\u00e8s, on a fait la sieste, Camille a travaill\u00e9 pour French Today et j\u2019ai \u00e9tudi\u00e9 un peu, et puis Camille a propos\u00e9 de suivre une visite guid\u00e9e de l\u2019Abbaye de Beauport qui commen\u00e7ait \u00e0 17 heures. On a march\u00e9 environ vingt minutes, et je m\u2019arr\u00eatais souvent pour prendre des photos : la baie de Paimpol est si jolie ! Mais Camille m\u2019a dit : \u00ab D\u00e9p\u00eache-toi Sunny\u202f! La visite guid\u00e9e commence dans cinq minutes. \u00bb Donc, j\u2019ai boug\u00e9 mes fesses et on est arriv\u00e9es \u00e0 l\u2019abbaye"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "7aafe155-28da-43f4-8305-2dc834f0d95a",
"name": "Generate French Audio",
"type": "n8n-nodes-base.httpRequest",
"position": [
300,
320
],
"parameters": {
"url": "=https://api.elevenlabs.io/v1/text-to-speech/{{ $json.voice_id }}",
"method": "POST",
"options": {
"response": {
"response": {
"responseFormat": "file"
}
}
},
"jsonBody": "={\"text\":\"{{ $json.text }}\",\"model_id\":\"eleven_multilingual_v2\",\"voice_settings\":{\"stability\":0.5,\"similarity_boost\":0.5}}",
"sendBody": true,
"sendQuery": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"queryParameters": {
"parameters": [
{
"name": "optimize_streaming_latency",
"value": "1"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "audio/mpeg"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "a8e75db9-4164-4332-bec3-01f91f40127f",
"name": "Translate Text to English",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
960,
320
],
"parameters": {
"text": "=Translate to English:\n{{ $json.text }}",
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "57ea8bc0-a372-41f8-9b7c-6aef0350d9eb",
"name": "Translate English text to speech",
"type": "n8n-nodes-base.httpRequest",
"position": [
1320,
320
],
"parameters": {
"url": "=https://api.elevenlabs.io/v1/text-to-speech/{{ $('Set ElevenLabs voice ID and text').first().json.voice_id }}",
"method": "POST",
"options": {},
"jsonBody": "={\"text\":\"{{ $json[\"text\"].replaceAll('\"', '\\\\\"').trim() }}\",\"model_id\":\"eleven_multilingual_v2\",\"voice_settings\":{\"stability\":0.5,\"similarity_boost\":0.5}}",
"sendBody": true,
"sendQuery": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"queryParameters": {
"parameters": [
{
"name": "optimize_streaming_latency",
"value": "1"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "accept",
"value": "audio/mpeg"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "d6bb0022-8c51-41f1-9159-139a45457201",
"name": "Add Filename",
"type": "n8n-nodes-base.code",
"position": [
540,
320
],
"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 item.binary.data.fileName = \"audio.mp3\";\n}\n\nreturn $input.all();"
},
"typeVersion": 2
}
],
"connections": {
"Add Filename": {
"main": [
[
{
"node": "Transcribe audio",
"type": "main",
"index": 0
}
]
]
},
"Transcribe audio": {
"main": [
[
{
"node": "Translate Text to English",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Translate Text to English",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Generate French Audio": {
"main": [
[
{
"node": "Add Filename",
"type": "main",
"index": 0
}
]
]
},
"Translate Text to English": {
"main": [
[
{
"node": "Translate English text to speech",
"type": "main",
"index": 0
}
]
]
},
"Set ElevenLabs voice ID and text": {
"main": [
[
{
"node": "Generate French Audio",
"type": "main",
"index": 0
}
]
]
},
"When clicking \"Execute Workflow\"": {
"main": [
[
{
"node": "Set ElevenLabs voice ID and text",
"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.
httpHeaderAuthopenAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow empowers content creators and developers to manually trigger custom code execution for tasks like transcribing audio files and generating AI-driven insights, saving hours of repetitive manual processing. It suits individuals or small teams needing flexible, on-demand automation without complex setups, particularly for prototyping ideas or handling ad-hoc requests. The key step involves an HTTP request to transcribe audio, seamlessly feeding into an OpenAI Chat Model integration that refines outputs through intelligent chaining, delivering polished results in moments.
Use this workflow when you require immediate, event-driven processing for audio transcription combined with AI summarisation, such as analysing meeting recordings or podcast episodes on the fly. Avoid it for high-volume, scheduled tasks better suited to cron-based triggers, or when real-time streaming is essential rather than manual initiation. Common variations include swapping the OpenAI model for other LLM providers or adding post-processing nodes for exporting transcripts to tools like Google Docs.
About this workflow
Manual Code. Uses manualTrigger, stickyNote, httpRequest, lmChatOpenAi. Event-driven trigger; 13 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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.
YouTube Video Analyzer with AI. Uses manualTrigger, lmChatOpenAi, lmChatOpenRouter, lmChatDeepSeek. Event-driven trigger; 21 nodes.
Code Http. Uses httpRequest, lmChatOpenAi, outputParserStructured, chainLlm. Event-driven trigger; 19 nodes.
Code Http. Uses httpRequest, lmChatOpenAi, outputParserStructured, chainLlm. Event-driven trigger; 19 nodes.
Converttofile Http. Uses lmChatOpenAi, googleSheets, httpRequest, openAi. Event-driven trigger; 18 nodes.
Blog Automation TEMPLATE. Uses scheduleTrigger, manualTrigger, googleSheets, lmChatOpenAi. Scheduled trigger; 35 nodes.