Which document data can the SDK extract?

Depending on the document type and analysis configuration, Docutain can return the following fields as structured JSON: Address and master data: up to three name lines, street, postal code, city, phone number and customer ID. Document and invoice data: date, invoice ID, amount and reference or payment reference. Bank details: one or more bank accounts with IBAN and BIC. Additional document-specific fields may be available depending on the document type and selected configuration.

What is the difference between OCR and data extraction?

OCR returns the recognized text of an image or PDF. Data extraction analyzes that text and returns selected business fields as a structured JSON string for further processing.

Why use the Docutain Data Capture SDK?

The Data Capture SDK reliably reads e-invoices and additionally processes images and PDFs through OCR, structured data extraction and searchable PDF creation. No separate e-invoice product is required. Imported files are supported on Android, iOS and Windows, and on Android and iOS processing can also be combined with mobile document scanning.

Does the Data Capture SDK support Windows?

Yes. On Windows, applications can import e-invoices, images or PDFs for local OCR, data extraction and PDF creation. Camera-based document scanning is available only on Android and iOS.

How can I test the Data Capture SDK?

Use our Android Showcase App or iOS Showcase App for a real-device evaluation. Test e-invoices and your own Android, iOS or Windows application with a free developer trial and representative files.

Data Capture, OCR & Data Extraction SDK

Process OCR, data extraction and e-invoices directly in your application.

Reliably read e-invoices and extract text plus structured data from images and PDFs in Android, iOS or Windows apps. Document scanning is available on Android and iOS.

Local OCR & data extraction – no external server connection

E-invoices, structured data & searchable PDFs

For Android, iOS and Windows

Pricing Try SDK for free

INVOICE

RECOGNIZED LOCALLY Structured document data

Invoice ID: 2026-0417
Date: 2026-07-24
Amount: EUR 359.44

Directly in your application

EASILY AUTOMATE & ACCELERATE PROCESSES

From image, PDF or e-invoice to usable document data

Load a document image, PDF or e-invoice and return full text plus structured document data as a JSON string. The result can be used to prefill forms, validate business data or hand information over to downstream workflows.

Depending on the document and analysis configuration, the SDK can return fields such as addresses, dates, invoice IDs, amounts and payment information including IBAN, BIC, payment state or SEPA creditor data.

On Android and iOS, input can come from the mobile Document Scanner, e-invoices or imported files. On Windows, e-invoices, images and PDFs are imported for OCR, data extraction and PDF creation; the Windows SDK does not provide camera scanning.

View the Windows data extraction documentation

INPUT

RECOGNIZED LOCALLY OCR TEXT + JSON

{
  "InvoiceId": "2026-0417",
  "Date": "2026-07-24",
  "Amount": "359.44"
}

Ready for downstream workflows

Request developer trial

ANDROID & IOS

Scan or import

Capture documents with the mobile scanner or load e-invoices, images and PDFs, then run OCR and data extraction locally.

CROSS-PLATFORM MOBILE

Use your preferred stack

Integrate through .NET MAUI, Flutter, React Native, Ionic, Capacitor, Cordova or Xamarin for Android and iOS apps.

WINDOWS

Import and analyze

Load e-invoices, images or PDFs for OCR, structured JSON data and searchable PDF creation. Camera scanning is not part of the Windows SDK.

AT A GLANCE

OCR and structured data extraction features

Full-text OCR recognition

Structured JSON results

Document fields such as address, date and invoice ID

Address, date & invoice fields

Amounts & payment data

Searchable PDF creation

Local offline processing

WHAT MAKES OUR DATA CAPTURE SDK SO SPECIAL

Text, document fields and searchable PDFs

Use OCR to retrieve the recognized text of a complete document or individual pages. For structured processing, the analysis API returns a JSON string with detected business fields.

Typical results include an address, document date, invoice ID and amount. Optional analysis settings add bank data, payment state, SEPA creditor information or GiroCode content when required by the workflow.

The recognized text can also be embedded in a searchable PDF. Your application remains in control of validation, field mapping and the handover to its own business formats.

All Docutain SDK features

WHAT DISTINGUISHES US AS A PROVIDER

Reliability. Support. Security.

Our goal is to make the integration of the OCR SDK & Data Capture SDK as fast as possible for you, so that you can focus on your core business. We support you with a simple Data Extraction API that enables use with just a few lines of code, mature documentation, and professional support.

We are aware of how important data protection is for companies. Therefore, Docutains Data Extraction API works locally on the device and 100% offline. At no time is data transferred to servers or third parties. Our offline solution - in contrast to server-side providers - also ensures fail-safety.

We attach great importance to a transparent and fair pricing model to give you as a company maximum planning security when integrating the mobile Data Extraction SDK.

What our customer Star Finanz says about the Data Extraction SDK

AT A GLANCE

SDK provider benefits

Fast integration of the Docutain Data Extraction SDK

Integration
in minutes

Docutain Data Extraction SDK data security

Guaranteed
data protection

Professional
support

Fair price with
highest quality

CUSTOMER EXPERIENCES

Data extraction in production applications

Real integrations show how Docutain works in existing applications and workflows.

Star Finanz Local document recognition in financial applications Read success story

SEEWARA Receipt capture and OCR in a business app Read success story

DESIGNED FOR DEVELOPERS

Powerful OCR & Data Extraction APIs

Use one SDK for full-text recognition, structured JSON data and searchable PDFs. Choose your platform: each example shows the complete flow from file import to usable JSON output.

import de.docutain.sdk.DocutainSDK
import de.docutain.sdk.dataextraction.DocumentDataReader

try {
    if (DocumentDataReader.loadFile(uri)) {
        val jsonData = DocumentDataReader.analyze()
        if (jsonData.isNotEmpty()) {
            // pass jsonData to your business process
        }
    } else {
        val error = DocutainSDK.getLastError()
    }
} catch (ex: SecurityException) {
    // the file is encrypted or the password is invalid
}

ADDITIONAL INFORMATION

STRUCTURED RESULT

What your downstream process receives

analyze() returns a JSON string. The fields included depend on the document and your analysis configuration.


{
  "Address": {
    "Name1": "Verbandsgemeindeverwaltung Nastätten",
    "Zipcode": "56352",
    "City": "Nastätten"
  },
  "Date": "2026-09-07",
  "Amount": "940.84",
  "InvoiceId": "20/VA06894/0009500"
}

USE CASES

OCR and data extraction are relevant for many industries

Logistics

Banking & Finance

Insurance

Evaluate OCR and data extraction with your own documents

Use the Showcase Apps to evaluate the Android/iOS workflow on a real device. For integration tests on mobile or Windows, request a developer trial license.

Android

Download

iOS

Download

FREQUENTLY ASKED QUESTIONS

Data Capture, OCR & Data Extraction SDK

From image, PDF or e-invoice to usable document data

Scan or import

Use your preferred stack

Import and analyze

OCR and structured data extraction features

Text, document fields and searchable PDFs

Reliability. Support. Security.

SDK provider benefits

Data extraction in production applications

Powerful OCR & Data Extraction APIs

What your downstream process receives

OCR and data extraction are relevant for many industries

Evaluate OCR and data extraction with your own documents

Android

iOS

Data Capture SDK: OCR and extraction questions

Contact us and receive your quote

Docutain SDKs for your platform

Data Capture, OCR & Data Extraction SDK

From image, PDF or e-invoice to usable document data

Scan or import

Use your preferred stack

Import and analyze

OCR and structured data extraction features

Text, document fields and searchable PDFs

Reliability. Support. Security.

SDK provider benefits

Data extraction in production applications

Powerful OCR & Data Extraction APIs

What your downstream process receives

OCR and data extraction are relevant for many industries

Evaluate OCR and data extraction with your own documents

Android

iOS

Data Capture SDK: OCR and extraction questions

Which document data can the SDK extract?

What is the difference between OCR and data extraction?

Why use the Docutain Data Capture SDK?

Does the Data Capture SDK support Windows?

How can I test the Data Capture SDK?

Success

Thank you for your inquiry.We will get back to you shortly.

Error

Sorry, your request could not be sent.Please email SDK@Docutain.com.

Contact us and receive your quote

Docutain SDKs for your platform

Thank you for your inquiry.

We will get back to you shortly.

Sorry, your request could not be sent.

Please email SDK@Docutain.com.