HumationHuman + Automation
Back to Catalog

WhatsApp receipt OCR & AI data extraction with Twilio, LlamaParse & Gemini

Gabriela MacoveiGabriela Macovei
119 views
2/3/2026
Data IngestionAutomationEmailSupabaseDatabase
Official Page

WhatsApp Receipt OCR & Data Extraction Suite

Categories: Accounting Automation • OCR Processing • AI Data Extraction • Business Tools

This workflow transforms WhatsApp into a fully automated receipt-processing system using advanced OCR, multi-model AI parsing, and structured data storage. By combining LlamaParse, Claude (OpenRouter), Gemini, Google Sheets, and Twilio, it eliminates manual data entry and delivers instant, reliable receipt digitization for any business.

What This Workflow Does

When a user sends a receipt photo or PDF via WhatsApp, the automation:

  1. Receives the file through Twilio WhatsApp
  2. Uploads and parses it with LlamaParse (high-res OCR + invoice preset)
  3. Extracts structured data using Claude + Gemini + a strict JSON parser
  4. Cleans and normalizes the data (dates, ABN, vendor, tax logic)
  5. Uploads the receipt to Google Drive
  6. Logs the extracted fields into a Google Sheet
  7. Replies to the user on WhatsApp with the extracted details
  8. Asks for confirmation via quick-reply buttons
  9. Updates the Google Sheet based on user validation

The result is a fast, scalable, human-free system for converting raw receipt photos into clean, structured accounting data.

Key Benefits

  • No friction for users: receipts are submitted simply by sending a WhatsApp message.
  • High-accuracy OCR: LlamaParse extracts text, tables, totals, vendors, tax, and ABN with impressive reliability.
  • Enterprise-grade data validation: complex logic ensures the correct interpretation of GST, included taxes, or unidentified tax amounts.
  • Multi-model extraction: Claude and Gemini both analyse the OCR output for more reliable result. We have one primary LLM and a secondary one.
  • Hands-off accounting: every receipt becomes a standardized row in Google Sheets.
  • Two-way WhatsApp communication: users can confirm or reject extracted data instantly.
  • Scalable architecture: perfect for businesses handling dozens or thousands of receipts monthly.

How It Works (Technical Overview)

1. Twilio → Webhook Trigger

The workflow starts when a WhatsApp message containing a media file hits your Twilio webhook.

2. Initial Google Sheets Logging

The MessageSid is appended to your tracking sheet to ensure every receipt is traceable.

3. LlamaParse OCR

The file is sent to LlamaParse with the invoice preset, high-resolution OCR, and table extraction enabled.
The workflow checks job completion before moving further.

4. LLM Data Extraction

The OCR markdown is analyzed using:

  • Claude Sonnet 4.5 (via OpenRouter)
  • Gemini 2.5 Pro
  • A strict structured JSON output parser
  • Custom JS cleanup logic

The system extracts:

  • Vendor
  • Cost
  • Tax (with multi-rule Australian GST logic)
  • Currency
  • Date (parsed + normalized)
  • ABN (validated and digit-normalized)

5. Google Drive Integration

The uploaded receipt is stored, shared, and linked back to the record in Sheets.

6. Google Sheets Update

Fields are appended/updated following a clean schema:

  • Vendor
  • Cost
  • Tax
  • Date
  • Currency
  • ABN
  • Public drive link
  • Status (Confirmed / Not confirmed)

7. User Response Flow

The user receives a summary of extracted data via WhatsApp.
Buttons allow them to approve or reject accuracy.
The Google Sheet updates accordingly.

Target Audience

This workflow is ideal for:

  • Accounting & bookkeeping firms
  • Outsourced finance departments
  • Small businesses tracking expenses
  • Field workers submitting receipts
  • Automation agencies offering DFY systems
  • CFOs wanting real-time expense visibility

Use Cases

  • Expense reconciliation
  • Automated bookkeeping
  • Receipt digitization & compliance
  • Real-time employee expense submission
  • Multi-client automation at accounting agencies

Required Integrations

  • Twilio WhatsApp (Business API number + webhook)
  • LlamaParse API
  • OpenRouter (Claude Sonnet)
  • Google Gemini API
  • Google Drive
  • Google Sheets

Setup Instructions (High-Level)

  1. Import the n8n workflow.
  2. Connect your Twilio WhatsApp account.
  3. Add API credentials for:
    • LlamaParse
    • OpenRouter
    • Google Gemini
    • Google Drive
    • Google Sheets
  4. Create your target Google Sheet.
  5. Configure your WhatsApp webhook URL in Twilio.
  6. Test with a sample receipt.

Why This System Works

  • Users send receipts using a tool they already use daily (WhatsApp).
  • LlamaParse provides state-of-the-art OCR for low-quality receipts.
  • Using multiple LLMs drastically increases accuracy for vendor, ABN, and tax extraction.
  • Advanced normalization logic ensures data is clean and accounting-ready.
  • Google Sheets enables reliable storage, reporting, and future integrations.
  • End-to-end automation replaces hours of manual work with instant processing.

Watch My Complete Build Process

Want to see exactly how I built this entire AI design system from scratch? I walk through the complete development process on my YouTube channel

n8n Workflow: WhatsApp Receipt OCR & AI Data Extraction with Twilio, LlamaParse & Gemini

This n8n workflow automates the process of extracting data from WhatsApp receipt images, parsing the information using AI, and storing it in a Google Sheet. It's designed to streamline expense tracking or any process requiring structured data from unstructured receipt images.

What it does

This workflow performs the following key steps:

  1. Receives WhatsApp Messages: Listens for incoming WhatsApp messages via a Twilio Webhook.
  2. Filters for Images: Checks if the incoming message contains an image attachment.
  3. Downloads Image: If an image is present, it downloads the image from the provided URL (e.g., Twilio Media URL).
  4. Uploads to Google Drive: Stores the downloaded receipt image in a specified Google Drive folder for archival.
  5. Extracts Text with LlamaParse: Sends the receipt image to LlamaParse (via a custom HTTP Request to OpenRouter) to perform OCR and extract structured data.
  6. Parses Data with Google Gemini: Uses a Google Gemini Chat Model with a Structured Output Parser to extract specific fields (e.g., total, vendor, date) from the LlamaParse output.
  7. Saves to Google Sheets: Appends the extracted data (vendor, total, date, and a link to the Google Drive image) as a new row in a designated Google Sheet.
  8. Handles Non-Image Messages: If the incoming WhatsApp message does not contain an image, it can be configured to send a response or simply end the workflow.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Twilio Account: Configured with a WhatsApp-enabled phone number and a webhook pointing to your n8n Webhook URL.
  • Google Account: With access to Google Drive and Google Sheets. You'll need credentials configured in n8n for both.
  • OpenRouter Account: An API key for OpenRouter to access LlamaParse or other LLMs.
  • Google Gemini API Key: Configured as a credential in n8n for the Google Gemini Chat Model.
  • A Google Sheet: A spreadsheet in Google Sheets with appropriate headers (e.g., "Vendor", "Total", "Date", "Image Link") where the extracted data will be stored.
  • A Google Drive Folder: A designated folder in Google Drive to store the uploaded receipt images.

Setup/Usage

  1. Import the workflow: Download the JSON provided and import it into your n8n instance.
  2. Configure Credentials:
    • Twilio Webhook: Set up your Twilio WhatsApp number's webhook to point to the "Webhook" node's URL in n8n.
    • Google Sheets: Create a Google Sheets credential in n8n and link it to the "Google Sheets" node. Specify your Spreadsheet ID and Sheet Name.
    • Google Drive: Create a Google Drive credential in n8n and link it to the "Google Drive" node. Specify the ID of the folder where you want to save the images.
    • OpenRouter: Create an HTTP Request credential for OpenRouter with your API key and link it to the "HTTP Request" node for LlamaParse.
    • Google Gemini: Create a Google Gemini Chat Model credential in n8n with your API key and link it to the "Google Gemini Chat Model" node.
  3. Customize LlamaParse HTTP Request: Ensure the HTTP Request node for LlamaParse is correctly configured with the LlamaParse API endpoint and any necessary headers/body for your OpenRouter setup.
  4. Customize Structured Output Parser: Adjust the Structured Output Parser node to define the exact schema (e.g., JSON structure) you expect for the extracted receipt data (e.g., vendor, total, date).
  5. Activate the workflow: Once all credentials and configurations are set, activate the workflow.
  6. Send a receipt: Send a WhatsApp message with a receipt image to your Twilio number to test the workflow. The extracted data should appear in your Google Sheet, and the image in your Google Drive.

Related Templates

Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets

This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.

Ranjan DailataBy Ranjan Dailata
161

Generate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax

Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions

Daniel NkenchoBy Daniel Nkencho
601

Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation

PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.

Le NguyenBy Le Nguyen
942