Every Document Type Your
Business Throws at It.
Xtracta processes more than invoices, receipts, bank statements, and contracts. The engine extracts structured data from passports, identity documents, purchase orders, remittance advice, eInvoices, and virtually any other document type. No templates. No manual setup. You tell the engine what data you need and it captures it.
One engine for every document type
Opening and closing balances validated automatically
No templates, no rules, learns from the documents
Purchase orders processed in seconds at any volume
eInvoices flow through the same workflow as PDFs
Choose a Document Type
Passports & Identity Documents
Purchase Orders
Remittance Advice
eInvoicing (Peppol)
Any Other Document
Remittance advice documents for accounts receivable reconciliation. Pre-built extraction models mean the engine works with little or no training. Highly scalable for peak payment periods when large volumes of remittance documents arrive at once. When remittance arrives alongside other documents like cheques, Xtracta processes everything together using document type detection and automatic splitting.
Capabilities
Data Xtracta extracts
Full Name
Date of Birth
Nationality
Document Number
Expiry Date
Issuing Authority
MRZ Data
Photo Page
Visa Details
Purchase orders and sales orders with full line item extraction, including complex orders with product variations (size, colour, style, technical specs). Processes orders in seconds and scales to handle hundreds or thousands simultaneously. Supports data lookups to match buyer product codes to supplier codes, validate shipping locations, and apply business logic.
Capabilities
Data Xtracta extracts
PO Number
Vendor Name
Buyer Name
Line Items
Product Codes
Quantities
Unit Prices
Delivery Address
Delivery Date
Total Amount
Remittance advice documents for accounts receivable reconciliation. Pre-built extraction models mean the engine works with little or no training. Highly scalable for peak payment periods when large volumes of remittance documents arrive at once. When remittance arrives alongside other documents like cheques, Xtracta processes everything together using document type detection and automatic splitting.
Capabilities
Data Xtracta extracts
Payer Name
Payment Date
Payment Amount
Invoice Numbers Referenced
Line Items
Amounts per Invoice
Payment Method
Reference Numbers
Xtracta is a certified Peppol access point. Software partners can offer eInvoicing alongside existing PDF, scan, and image-based invoice capture with no additional development. eInvoices flow through the exact same workflow as extracted PDF invoices, meaning one system to configure, one API integration, and seamless switching as vendors move to eInvoicing.
Capabilities
Data Xtracta extracts
Structured invoice data delivered via the Peppol network
Same data matching and transformation tools as PDF invoice processing
Unified workflow alongside traditional document capture
Xtracta is not limited to the document types listed on this site. The engine reads layout, language, and structure to understand any document format. If your business processes a document type not covered here, talk to us. If the data is on the page, Xtracta can capture it.
Capabilities
Data Xtracta extracts
You tell the engine what data you need
Header fields, line items, tables, values, dates, names, references
Unified workflow alongside traditional document capture
How Documents Get Into Xtracta
Every input method and format works for every document type. No separate systems.
Input Methods
API Upload
Email (dedicated address)
SFTP (bulk)
Web Portal (drag and drop)
Mobile App
Image Capture SDK
Peppol Network (eInvoicing)
File Formats
DOC
XLS
CSV
JPG
PNG
TIFF
Scanned documents
Photographed documents
Multi-page PDFs
Mixed document bundles
TIFF
What Makes It Work Across Every Document Type
Document Type Auto-Detection
Drop a hundred mixed documents in. Xtracta sorts them.
The engine identifies what type of document it’s looking at, separates mixed uploads, splits multi-page PDFs, and routes each document through the right workflow. No manual sorting.
Data Matching and Validation
Clean data before it reaches your systems.
Database lookups, mathematical formula checks, value transformation, and external data service connections. Buyer codes matched to supplier codes. Dates formatted. Currencies normalised. Business logic applied.
Click-and-Train for New Formats
If the engine hasn’t seen it before, your team shows it once.
The Engine Learning Screen lets users click on data in the document to teach the engine what to capture. One interaction improves accuracy for that document type going forward. Set and forget.
White-Label and Embed
Your customers see your product. Xtracta stays invisible.
Every document type, every input method, and every capability is available through the API. White-label the UI, brand the mobile app, embed the SDK. Your product, powered by Xtracta.
FAQ
Invoices, receipts, bank statements, contracts, passports, national IDs, driver’s licences, purchase orders, remittance advice, eInvoices (via Peppol), and virtually any other structured or semi-structured document. If the data is on the page, Xtracta can capture it.
Yes. Xtracta supports passports, national IDs, driver’s licences, workplace IDs, vaccination certificates, and travel visas for identity verification workflows. Pre-trained models handle common identity documents out of the box. The image capture SDK supports mobile capture with automatic cropping, flattening, and front-and-back stitching.
Peppol is a global network for exchanging electronic business documents. Xtracta is a certified Peppol access point. eInvoices flow through the same workflow as PDF invoices, meaning one system, one API, and seamless switching as vendors adopt eInvoicing. No additional development required for existing Xtracta partners.
Yes. The engine handles purchase orders with product variations (size, colour, technical specs), thousands of line items, and mismatched buyer/supplier product codes. Data lookups match codes, validate shipping locations, and apply business logic before the data reaches your systems.
Remittance advice documents confirm that an invoice has been paid. Xtracta extracts payer details, payment amounts, referenced invoice numbers, and line items to speed up accounts receivable reconciliation. Pre-built models mean it works with minimal setup.
Yes. Drop a bundle of mixed documents into Xtracta. The engine detects the document type of each, separates them, splits multi-page PDFs, and routes each through the right extraction workflow. No manual sorting required.
Learn more: How Xtracta Works – For Software Companies · For Partners · Customer Stories
Got a Document? Xtracta Can Read It.
This isn’t a self-service sandbox. Our team sets it up with you.
Your data, from day one.