How it works
AI trained on millions of handwritten pages
Transkribus uses artificial intelligence trained on more than 30 million words from historical documents spanning five centuries. The AI analyzes the shape and flow of each letter, recognizing patterns even in the most difficult old German handwriting. Your document is processed line by line and converted into readable digital text.
Reads Kurrent, Sütterlin, Fraktur, and other old German scripts
300+ public models for different handwriting styles and time periods
Works with phone photos or high-resolution scans
Family research
Finally read your ancestors' letters and documents
Millions of Americans have German-speaking ancestors who left behind letters, diaries, and official documents written in old German scripts. These scripts – Kurrent, Sütterlin, and Fraktur – are nearly impossible to read without training. Transkribus translates them into modern text automatically.
Immigration letters and correspondence from the old country
Church records: baptisms, marriages, and death certificates
Ship manifests and emigration documents
Family bibles, diaries, and personal notebooks
Beyond the demo
The full platform for historical documents
The demo above gives you a taste. The full Transkribus platform lets you process thousands of pages, train custom AI models on your specific handwriting, search across all your documents, and export in any format you need.
Train custom models on your family's specific handwriting
Full-text search across all your transcribed documents
Export as TXT, DOCX, PDF, TEI-XML, or PAGE XML
Collaborate with family members and share collections
What you can transcribe
Common documents in old German handwriting
If you're researching German, Austrian, or Swiss ancestry, you'll encounter a wide range of handwritten and printed documents in old scripts. Transkribus handles them all – whether they're from a church archive, a family attic, or a genealogy database.
Letters from immigrant ancestors to family back home
Kirchenbücher (church books) with birth, marriage, and death records
Military records and wartime correspondence (Feldpost)
Land deeds, wills, and legal contracts
Diaries, recipe books, and household journals
Printed Fraktur books and newspapers
Background
What are old German scripts?
If you've ever looked at a letter or document from a German-speaking ancestor and couldn't read a single word – you're not alone. Before 1941, most German speakers used very different handwriting and print styles than what we know today. Here's a quick guide to the scripts you'll encounter:
Kurrent – the standard German handwriting from the 1500s to the early 1900s
Sütterlin – a simplified school script introduced in 1911, used until 1941
Fraktur – the "broken" Gothic print typeface used in books and newspapers
Antiqua – the Latin print style that gradually replaced Fraktur
Offenbacher Schrift – replaced Sütterlin briefly from 1935
The technology
How does old German handwriting recognition work?
Handwriting recognition (HTR – Handwritten Text Recognition) uses deep learning neural networks to convert images of handwritten text into machine-readable characters. Unlike OCR for printed text, HTR must handle the infinite variation in human handwriting – different letter shapes, connected strokes, and personal styles that change across centuries.
Neural networks trained on millions of handwritten samples
Layout analysis detects lines and text regions automatically
Character-level recognition handles connected and cursive writing
Language models improve accuracy by understanding word context
Ready to read your ancestors' handwriting?
Create a free account to process unlimited documents, train custom models, and unlock the full platform.
50 free credits every month – No credit card required
200M+Pages processed
500K+Users worldwide
300+Public AI models