HumationHuman + Automation
Back to Catalog

Process Thai documents with TyphoonOCR & AI to Google Sheets (multi-page PDF)

Jaruphat J.Jaruphat J.
489 views
2/3/2026
GitHubSlackNotificationsAutomationPull Request
Official Page

⚠️ Note: This template requires a community node and works only on self-hosted n8n installations. It uses the Typhoon OCR Python package, pdfseparate from poppler-utils, and custom command execution. Make sure to install all required dependencies locally.

Who is this for?

This template is designed for developers, back-office teams, and automation builders (especially in Thailand or Thai-speaking environments) who need to process multi-file, multi-page Thai PDFs and automatically export structured results to Google Sheets.

It is ideal for:

  • Government and enterprise document processing
  • Thai-language invoices, memos, and official letters
  • AI-powered automation pipelines that require Thai OCR

What problem does this solve?

Typhoon OCR is one of the most accurate OCR tools for Thai text, but integrating it into an end-to-end workflow usually requires manual scripting and handling multi-page PDFs. This template solves that by:

  • Splitting PDFs into individual pages
  • Running Typhoon OCR on each page
  • Aggregating text back into a single file
  • Using AI to extract structured fields
  • Automatically saving structured data into Google Sheets

What this workflow does

wf22.gif

  • Trigger: Manual execution or any n8n trigger node
  • Load Files: Read PDFs from a local doc/multipage folder
  • Split PDF Pages: Use pdfinfo and pdfseparate to break PDFs into pages
  • Typhoon OCR: Run OCR on each page via Execute Command
  • Aggregate: Combine per-page OCR text
  • LLM Extraction: Use AI (e.g., GPT-4, OpenRouter) to extract fields into JSON
  • Parse JSON: Convert structured JSON into a tabular format
  • Google Sheets: Append one row per file into a Google Sheet
  • Cleanup: Delete temp split pages and move processed PDFs into a Completed folder

Setup

  1. Install Requirements

    • Python 3.10+
    • typhoon-ocr: pip install typhoon-ocr
    • poppler-utils: provides pdfinfo, pdfseparate
    • qpdf: backup page counting

  2. Create folders

    • /doc/multipage for incoming files
    • /doc/tmp for split pages
    • /doc/multipage/Completed for processed files

  3. Google Sheet

    • Create a Google Sheet with column headers like: 
      book_id | date | subject | to | attach | detail | signed_by | signed_by2 | contact_phone | contact_email | contact_fax | download_url

  4. API Keys

    • Export your TYPHOON_OCR_API_KEY and OPENAI_API_KEY (or use credentials in n8n)

How to customize this workflow

  • Replace the LLM provider in the “Structure Text to JSON with LLM” node (supports OpenRouter, OpenAI, etc.)
  • Adjust the JSON schema and parsing logic to match your documents
  • Update Google Sheets mapping to fit your desired fields
  • Add trigger nodes (Dropbox, Google Drive, Webhook) to automate file ingestion

About Typhoon OCR

Typhoon is a multilingual LLM and NLP toolkit optimized for Thai. It includes typhoon-ocr, a Python OCR package designed for Thai-centric documents. It is open-source, highly accurate, and works well in automation pipelines. Perfect for government paperwork, PDF reports, and multi-language documents in Southeast Asia.

Deployment Option

You can also deploy this workflow easily using the Docker image provided in my GitHub repository: https://github.com/Jaruphat/n8n-ffmpeg-typhoon-ollama

This Docker setup already includes n8n, ffmpeg, Typhoon OCR, and Ollama combined together, so you can run the whole environment without installing each dependency manually.

n8n Workflow: Process Thai Documents with TyphoonOCR & AI to Google Sheets (Multi-Page PDF)

This n8n workflow automates the extraction of text from multi-page Thai PDF documents using a local OCR solution (TyphoonOCR via shell command), processes the extracted text with an AI model (OpenRouter Chat Model), and then logs the results into a Google Sheet. It's designed to handle documents page by page and aggregate the findings.

What it does

This workflow performs the following steps:

  1. Manual Trigger: Starts the workflow manually when executed.
  2. Read/Write Files from Disk: Reads a specified multi-page PDF document from disk.
  3. Loop Over Items (Split in Batches): Splits the PDF into individual pages (or processes it as a single item if not multi-page) to allow for page-by-page OCR processing.
  4. Execute Command (TyphoonOCR): For each page, it executes a shell command to run TyphoonOCR, extracting text from the PDF page. The output is saved to a temporary text file.
  5. Read/Write Files from Disk: Reads the text content from the temporary file created by TyphoonOCR.
  6. Basic LLM Chain (OpenRouter Chat Model): Sends the extracted text to an AI model (via OpenRouter) for processing. This step likely involves prompting the AI to extract specific information or summarize the Thai text.
  7. Code: Processes the output from the AI model, likely parsing it into a structured format suitable for Google Sheets.
  8. Aggregate: Combines the processed data from all pages/items back into a single dataset.
  9. Google Sheets: Appends the final, aggregated and structured data to a specified Google Sheet.

Prerequisites/Requirements

Before running this workflow, you will need:

  • n8n Instance: A running n8n instance where this workflow will be imported.
  • TyphoonOCR Installation: TyphoonOCR must be installed and configured on the server hosting your n8n instance, accessible via shell commands.
  • Google Account: A Google account with access to Google Sheets. You will need to set up Google Sheets credentials in n8n.
  • OpenRouter Account: An OpenRouter account with an API key to access their chat models. You will need to configure OpenRouter credentials in n8n.
  • PDF Document: A multi-page PDF document (preferably in Thai) to be processed. The path to this document needs to be configured in the "Read/Write Files from Disk" node.
  • Temporary Directory: A writable directory on the n8n host for temporary files generated by TyphoonOCR.

Setup/Usage

  1. Import the Workflow:
    • Download the workflow JSON provided.
    • In your n8n instance, click "Workflows" in the left sidebar.
    • Click "New" or "Import from JSON" and paste the workflow JSON.
  2. Configure Credentials:
    • Google Sheets: Locate the "Google Sheets" node and click on the "Credentials" field. Select an existing Google Sheets OAuth2 credential or create a new one, granting n8n access to your Google Sheets.
    • OpenRouter Chat Model: Locate the "OpenRouter Chat Model" node and configure your OpenRouter API key.
  3. Configure File Paths:
    • Read/Write Files from Disk (initial): In the first "Read/Write Files from Disk" node, specify the absolute path to your input PDF document.
    • Execute Command: Review the Execute Command node. Ensure the command correctly calls your TyphoonOCR installation and specifies the input PDF page and output text file paths. Adjust the paths for temporary files as needed, ensuring they are accessible and writable by the n8n user.
    • Read/Write Files from Disk (after OCR): In the second "Read/Write Files from Disk" node, ensure the file path matches the output path configured in the Execute Command node.
  4. Configure Google Sheet:
    • In the "Google Sheets" node, specify the Spreadsheet ID and the Sheet Name where you want the extracted data to be appended.
  5. Configure AI Prompt (Optional but Recommended):
    • In the "Basic LLM Chain" node, review and adjust the prompt to the OpenRouter Chat Model to precisely define what information you want to extract or how you want the Thai text to be processed.
  6. Test and Activate:
    • Save the workflow.
    • Click "Execute Workflow" to run a test. Monitor the output of each node to ensure data is flowing as expected and errors are not encountered.
    • Once satisfied, activate the workflow by toggling the "Active" switch in the top right corner.

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