Luis R. This workflow corresponds to n8n.io template #15927 — we link there as the canonical source.
This workflow follows the HTTP Request → OpenAI 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": "SixmnXUWppIg1Tbf",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Voice Message Transcription + Intent Classification",
"tags": [],
"nodes": [
{
"id": "1054438f-1ec7-4eb0-9fbe-6ae413822239",
"name": "When clicking \u2018Execute workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
0,
0
],
"parameters": {},
"typeVersion": 1
},
{
"id": "0ca12ee3-7651-4a23-8a69-a8ccb963ef6d",
"name": "Sample Audio (JFK)",
"type": "n8n-nodes-base.set",
"position": [
208,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "cd9f80ef-64b2-4faa-9ebf-2d9b3729ee08",
"name": "audioUrl",
"type": "string",
"value": "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
},
{
"id": "7e5e9364-34c4-424d-b2a5-25b4bae141b5",
"name": "mimeType",
"type": "string",
"value": "audio/flac"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "af3ccc0c-2cad-4969-8177-34be42de7c1a",
"name": "Download Audio",
"type": "n8n-nodes-base.httpRequest",
"position": [
416,
0
],
"parameters": {
"url": "={{ $json.audioUrl }}",
"options": {
"response": {
"response": {
"responseFormat": "file"
}
}
}
},
"typeVersion": 4.4
},
{
"id": "3a13aa42-7937-42e5-bd35-874227b579a3",
"name": "Whisper Transcription1",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
624,
0
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "transcribe"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "ca907376-733c-4918-b685-b95397687adc",
"name": "Edit Fields",
"type": "n8n-nodes-base.set",
"position": [
832,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "3bb22c6d-49d7-4c23-91e5-8a5a5dc42272",
"name": "=transcript",
"type": "string",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e55ba4e6-a5e3-4b2a-9aef-406e10fbc8ea",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
-560
],
"parameters": {
"width": 928,
"height": 544,
"content": "## \ud83c\udf99\ufe0f Voice Message Transcription + Intent Classification with OpenAI Whisper\n\nTranscribes audio messages and automatically classifies intent using GPT-4o-mini.\nDemo uses the official OpenAI test audio (JFK speech).\n\n**How to use:**\n1. Add your OpenAI API credentials in Nodes 3 and 5\n2. Replace the audioUrl in Node 1 with your own audio source\n3. Connect to your webhook (Evolution API, Twilio, WhatsApp Cloud API, etc.)\n4. Replace the response nodes with your own logic per intent\n\n**Flow:**\nAudio URL \u2192 Download \u2192 Transcribe (Whisper) \u2192 Classify Intent (GPT-4o-mini) \u2192 Route by Intent\n\n**Intent categories:**\n- `GREETING` \u2014 hello, hi, hey, good morning\n- `QUESTION` \u2014 any question detected\n- `REQUEST` \u2014 specific ask or request\n- `OTHER` \u2014 everything else\n\n**Output:**\n- `transcript` \u2014 plain text transcription\n- `intent` \u2014 classified category in uppercase\n\n**Compatible with:**\nEvolution API \u00b7 Twilio \u00b7 WhatsApp Cloud API \u00b7 Any webhook delivering audio URLs\n\n**Author:** Luis Rend\u00f3n\n\ud83d\udd17 xiaoluxtl.github.io/luis-r"
},
"typeVersion": 1
},
{
"id": "cea5fb78-3725-4b65-9748-a61e85a201d8",
"name": "Extract Intent",
"type": "n8n-nodes-base.set",
"position": [
352,
256
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "079a9971-4d49-4799-afab-098c1bc6d503",
"name": "intent",
"type": "string",
"value": "={{ $json.output[0].content[0].text.trim().toUpperCase() }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e85c9785-812a-4961-98e4-3f5b37c7306a",
"name": "Route by Intent",
"type": "n8n-nodes-base.switch",
"position": [
544,
432
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "greeting",
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b1ae04ad-ca42-41fc-a970-0e99b2f1bece",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "GREETING",
"rightValue": "={{ $json.intent }}"
}
]
},
"renameOutput": true
},
{
"outputKey": "question",
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "fa130c67-732e-4dab-bab7-824396846dc2",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "QUESTION",
"rightValue": "={{ $json.intent }}"
}
]
},
"renameOutput": true
},
{
"outputKey": "request",
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "81486d2d-d77f-4f55-9d72-79fd977e8a92",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "REQUEST",
"rightValue": "={{ $json.intent }}"
}
]
},
"renameOutput": true
},
{
"outputKey": "other",
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "7222b25e-bc79-4e20-9ca7-fdace02b92aa",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "OTHER",
"rightValue": "={{ $json.intent }}"
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.4
},
{
"id": "a78155cc-5186-4dcd-891d-62cd5b9f6ab6",
"name": "Response - Greeting",
"type": "n8n-nodes-base.set",
"position": [
752,
224
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0e4606de-3923-4e59-ab9f-b2641372ede7",
"name": "response",
"type": "string",
"value": "\ud83d\udc4b Hello! How can I help you today?"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "57a7f814-6bd4-4e55-8a97-9618523587ed",
"name": "Response - Question",
"type": "n8n-nodes-base.set",
"position": [
752,
368
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0e4606de-3923-4e59-ab9f-b2641372ede7",
"name": "response",
"type": "string",
"value": "\ud83e\udd14 I detected a question. Routing to Q&A handler..."
}
]
}
},
"typeVersion": 3.4
},
{
"id": "eafc5168-08c3-472d-badd-71951b3922fb",
"name": "Response - Request",
"type": "n8n-nodes-base.set",
"position": [
752,
528
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0e4606de-3923-4e59-ab9f-b2641372ede7",
"name": "response",
"type": "string",
"value": "\ud83d\udccb Request received. Processing your request..."
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e7ab1c5c-c57a-4134-88c4-4f26751507cd",
"name": "Response - Others",
"type": "n8n-nodes-base.set",
"position": [
752,
688
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0e4606de-3923-4e59-ab9f-b2641372ede7",
"name": "response",
"type": "string",
"value": "\ud83d\udcdd Message transcribed and logged successfully."
}
]
}
},
"typeVersion": 3.4
},
{
"id": "dd65f3ab-a084-4c8f-8c01-a786b3b4dea7",
"name": "Intent Classifier",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
0,
256
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "GPT-4O-MINI"
},
"options": {},
"responses": {
"values": [
{
"content": "=Classify this transcript into exactly one word:\nGREETING, QUESTION, REQUEST, or OTHER.\n\nTranscript: \"{{ $json.transcript }}\"\n\nReply with ONLY the category word, nothing else.\n"
}
]
},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"executionOrder": "v1"
},
"versionId": "5c70b563-1d98-4035-b4fa-5989ca8ea075",
"connections": {
"Edit Fields": {
"main": [
[
{
"node": "Intent Classifier",
"type": "main",
"index": 0
}
]
]
},
"Download Audio": {
"main": [
[
{
"node": "Whisper Transcription1",
"type": "main",
"index": 0
}
]
]
},
"Extract Intent": {
"main": [
[
{
"node": "Route by Intent",
"type": "main",
"index": 0
}
]
]
},
"Route by Intent": {
"main": [
[
{
"node": "Response - Greeting",
"type": "main",
"index": 0
}
],
[
{
"node": "Response - Question",
"type": "main",
"index": 0
}
],
[
{
"node": "Response - Request",
"type": "main",
"index": 0
}
],
[
{
"node": "Response - Others",
"type": "main",
"index": 0
}
]
]
},
"Intent Classifier": {
"main": [
[
{
"node": "Extract Intent",
"type": "main",
"index": 0
}
]
]
},
"Sample Audio (JFK)": {
"main": [
[
{
"node": "Download Audio",
"type": "main",
"index": 0
}
]
]
},
"Whisper Transcription1": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Sample Audio (JFK)",
"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.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow downloads an audio file, transcribes it with OpenAI Whisper, classifies the transcript intent using OpenAI GPT-4o-mini, and returns a simple response message based on the detected category. Runs when you manually execute the workflow. Sets a sample audio URL (JFK…
Source: https://n8n.io/workflows/15927/ — 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.
Domain Outbound Machine is an n8n workflow designed to fully automate the domain sales process: lead generation, email extraction, personalized outreach, and automated email sending. It also stores ex
Google Sheets, HTTP Request, Gmail +1
Social Media Audio Extractor. Uses telegramTrigger, telegram, openAi, httpRequest. Event-driven trigger; 31 nodes.
Telegram Trigger, Telegram, OpenAI +2
Baby Chaganti. Uses httpRequest, googleDrive, youTube, openAi. Event-driven trigger; 23 nodes.
HTTP Request, Google Drive, YouTube +1
Monitor YouTube channels, fetch stats, classify videos as viral (≥ 1000 likes) or normal, and auto‑generate LinkedIn/email summaries with GPT‑4. Deliver via Gmail or SMTP. Clear node names, examples,
RSS Feed Read, HTTP Request, OpenAI +1
Overview: This workflow automates the full pipeline of preparing scraped leads and loading them into an Instantly campaign for cold outreach.It begins by pulling rows from a Google Sheet that contains
Google Sheets, Telegram, OpenAI +1