Spiritec This workflow corresponds to n8n.io template #13504 — we link there as the canonical source.
This workflow follows the HTTP Request → WhatsApp Trigger 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": "I2UoQP8Af3EKxGGX",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Onboardly AI Agent - WhatsApp Document Collection",
"tags": [],
"nodes": [
{
"id": "e7886fe8-d9c6-4b65-9670-1fe6f4fe3889",
"name": "AWS GetDocumentAnalysis",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1168,
-448
],
"parameters": {
"url": "https://textract.us-east-1.amazonaws.com/",
"method": "POST",
"options": {},
"jsonBody": "={\n \"JobId\": \"{{ $json.data.parseJson().JobId}}\"\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"headerParameters": {
"parameters": [
{
"name": "X-Amz-Target",
"value": "Textract.GetDocumentAnalysis"
},
{
"name": "Content-Type",
"value": "application/x-amz-json-1.1"
}
]
},
"nodeCredentialType": "aws"
},
"credentials": {
"aws": {
"name": "<your credential>"
}
},
"typeVersion": 4.3
},
{
"id": "50ea7ddb-e2e3-4c57-be98-1f2db5669201",
"name": "AWS StartDocumentAnalysis",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1616,
-448
],
"parameters": {
"url": "https://textract.us-east-1.amazonaws.com/",
"method": "POST",
"options": {},
"jsonBody": "={\n \"DocumentLocation\": {\n \"S3Object\": {\n \"Bucket\": \"{{ $json.Bucket }}\",\n \"Name\": \"{{ $json.Key }}\"\n }\n },\n \"FeatureTypes\": [\"FORMS\", \"TABLES\"]\n}\n ",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"headerParameters": {
"parameters": [
{
"name": "X-Amz-Target",
"value": "Textract.StartDocumentAnalysis"
},
{
"name": "Content-Type",
"value": "application/x-amz-json-1.1"
}
]
},
"nodeCredentialType": "aws"
},
"credentials": {
"aws": {
"name": "<your credential>"
}
},
"typeVersion": 4.3
},
{
"id": "ac51229d-ec18-4900-a87f-e572a11ebf8f",
"name": "Download File from S3",
"type": "n8n-nodes-base.awsS3",
"position": [
-1840,
-448
],
"parameters": {
"fileKey": "={{ $json.Key }}",
"bucketName": "={{ $json.Bucket }}"
},
"credentials": {
"aws": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "5c690c78-dac9-4654-a6f2-4c69147f261d",
"name": "Upload File to S3",
"type": "n8n-nodes-base.awsS3",
"position": [
-2064,
-448
],
"parameters": {
"fileName": "={{ $('WhatsApp Trigger').item.json.messages[0].document.filename }}",
"operation": "upload",
"bucketName": "onboardly-ai",
"additionalFields": {}
},
"credentials": {
"aws": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "822414b6-a00b-4370-b435-a2361267b4f7",
"name": "File Download",
"type": "n8n-nodes-base.httpRequest",
"position": [
-2288,
-448
],
"parameters": {
"url": "={{ $json.url }}",
"options": {
"response": {
"response": {
"responseFormat": "file"
}
}
},
"authentication": "predefinedCredentialType",
"nodeCredentialType": "whatsAppApi"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.3
},
{
"id": "74c15e4b-acc2-4e80-8001-b8592cf4aa59",
"name": "Get PDF",
"type": "n8n-nodes-base.httpRequest",
"position": [
-2512,
-448
],
"parameters": {
"url": "=https://graph.facebook.com/v24.0/{{ $('WhatsApp Trigger').item.json.messages[0].document.id }}",
"options": {},
"sendQuery": true,
"authentication": "predefinedCredentialType",
"queryParameters": {
"parameters": [
{
"name": "phone_number_id",
"value": "={{ $('WhatsApp Trigger').item.json.metadata.phone_number_id }}"
}
]
},
"nodeCredentialType": "whatsAppApi"
},
"credentials": {
"whatsAppApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.3
},
{
"id": "4b4920e8-2fa8-4bf1-913a-e658bea83736",
"name": "WhatsApp Trigger",
"type": "n8n-nodes-base.whatsAppTrigger",
"position": [
-2736,
-448
],
"parameters": {
"options": {
"messageStatusUpdates": [
"all"
]
},
"updates": [
"messages"
]
},
"credentials": {
"whatsAppTriggerApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "29c7c835-7a51-4cc9-abf9-9cf3cb9ce73c",
"name": "Wait for Processing Time",
"type": "n8n-nodes-base.wait",
"position": [
-1392,
-448
],
"parameters": {
"amount": 30
},
"typeVersion": 1.1
},
{
"id": "c6d13085-5dc3-4f5e-9085-bf9dd93d8102",
"name": "Extract Text",
"type": "n8n-nodes-base.code",
"position": [
-944,
-448
],
"parameters": {
"jsCode": "const items = $input.all();\n\nconst results = items.map(item => {\n const raw = item.json.data; \n const textract = typeof raw === 'string'\n ? JSON.parse(raw)\n : raw;\n\n const blocks = textract.Blocks || [];\n\n const lines = blocks\n .filter(b => b.BlockType === 'LINE' && b.Text)\n .map(b => b.Text);\n\n return {\n json: {\n text: lines.join('\\n')\n }\n };\n});\n\nreturn results;\n"
},
"typeVersion": 2
},
{
"id": "5751ca71-fb58-4506-947d-f95c9ef41a29",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-3616,
-656
],
"parameters": {
"width": 752,
"height": 528,
"content": "## \ud83d\udfe8 **MAIN STICKY \u2014 WhatsApp PDF OCR Workflow**\n\n**How it Works**\n\nThis workflow automatically extracts text from PDF documents sent via WhatsApp. When a message containing a PDF arrives, the file is downloaded from the WhatsApp media URL and uploaded to your AWS S3 bucket. A Textract analysis job is then started to perform OCR on the stored PDF. After a short wait, the workflow retrieves the results from Textract and converts them into clean, ordered text. The extracted output is returned for further processing such as AI analysis, storage, or automation.\n\n**Setup Steps**\n1. Connect your WhatsApp integration (e.g., webhook from WhatsApp Cloud API).\n2. Add AWS credentials with permission for S3 upload and Textract analysis.\n3. Set your S3 bucket name and Textract region in the AWS nodes.\n4. Ensure HTTP Request nodes are authenticated for WhatsApp media access.\n5. Activate the workflow and send a PDF via WhatsApp to test.\n\n**Good to Know**\n* Supports both scanned and digital PDFs.\n* Textract pricing is per page; processing time varies by file size.\n* S3 acts as the required temporary storage layer."
},
"typeVersion": 1
},
{
"id": "8eb1a8b8-a3a9-4f77-b6d5-2a92e1f7919d",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2800,
-656
],
"parameters": {
"color": 7,
"width": 656,
"height": 528,
"content": "## Whatsapp Input"
},
"typeVersion": 1
},
{
"id": "dc4fc46b-93d3-4193-ae55-febb76236415",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2128,
-656
],
"parameters": {
"color": 7,
"width": 432,
"height": 528,
"content": "## AWS S3 Handling"
},
"typeVersion": 1
},
{
"id": "252dd1ba-471d-4cb8-9dad-64c899098a6e",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1664,
-656
],
"parameters": {
"color": 7,
"width": 640,
"height": 528,
"content": "## AWS Textract Processing"
},
"typeVersion": 1
},
{
"id": "137923f7-dd0a-4138-b4b8-b298f29a6d49",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1008,
-656
],
"parameters": {
"color": 7,
"width": 256,
"height": 528,
"content": "## Output Cleanup"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "b71bd0f8-1f4f-46e6-9f1d-76698182a335",
"connections": {
"Get PDF": {
"main": [
[
{
"node": "File Download",
"type": "main",
"index": 0
}
]
]
},
"Extract Text": {
"main": [
[]
]
},
"File Download": {
"main": [
[
{
"node": "Upload File to S3",
"type": "main",
"index": 0
}
]
]
},
"WhatsApp Trigger": {
"main": [
[
{
"node": "Get PDF",
"type": "main",
"index": 0
}
]
]
},
"Upload File to S3": {
"main": [
[
{
"node": "Download File from S3",
"type": "main",
"index": 0
}
]
]
},
"Download File from S3": {
"main": [
[
{
"node": "AWS StartDocumentAnalysis",
"type": "main",
"index": 0
}
]
]
},
"AWS GetDocumentAnalysis": {
"main": [
[
{
"node": "Extract Text",
"type": "main",
"index": 0
}
]
]
},
"Wait for Processing Time": {
"main": [
[
{
"node": "AWS GetDocumentAnalysis",
"type": "main",
"index": 0
}
]
]
},
"AWS StartDocumentAnalysis": {
"main": [
[
{
"node": "Wait for Processing Time",
"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.
awswhatsAppApiwhatsAppTriggerApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n template demonstrates how to automatically extract text content from PDF documents received via WhatsApp messages using OCR.
Source: https://n8n.io/workflows/13504/ — 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.
WhatsApp Multi-Agent v2 (Cloud API). Uses whatsAppTrigger, httpRequest, airtable, errorTrigger. Event-driven trigger; 39 nodes.
WhatsApp Trigger, HTTP Request, Airtable +1
WhatsApp Multi-Agent (Security Patched). Uses airtable, httpRequest, errorTrigger, whatsAppTrigger. Event-driven trigger; 36 nodes.
Airtable, HTTP Request, Error Trigger +1
Transform your salon/service business with this streamlined WhatsApp automation system featuring Claude integration, zero-setup database management, and intelligent conversation handling. Claude MCP I
WhatsApp Trigger, WhatsApp, Redis +11
CashMate – Your AI-Powered WhatsApp Finance Agent Turn WhatsApp into a smart finance assistant that auto-registers you, logs transactions in natural language, extracts data from receipts and voice not
Tool Code, Output Parser Structured, Tool Calculator +6
This workflow creates a complete AI-powered restaurant ordering system through WhatsApp. It receives customer messages, processes multimedia content (text, voice, images, PDFs, location), uses GPT-4 t
OpenAI Chat, Memory Postgres Chat, HTTP Request +6