Transkribus
by READ-COOP
Transkribus is a platform for recognising handwritten and printed text in images of historical documents, run by READ-COOP, a European cooperative in Innsbruck owned by universities, archives, libraries and individuals. Archives, libraries, historians and other researchers use it to transcribe, search and publish manuscripts, registers and printed books, through a web app, an API, an on-premises version and a scanning app. The vendor says neural networks read each line character by character, and that it offers more than 300 public AI models, including its own general model Text Titan, plus layout analysis, table and field extraction, entity tagging and custom model training on as few as 50 transcribed pages. Users correct the recognised text in a built-in editor, and the vendor says recognition accuracy depends mainly on how users train and handle the models.
Transparency Score
Weighted across four pillars · updated October 19, 2026
Capabilities
Vendor Information
Complete information about the vendor/provider of this AI application
Infrastructure
Platforms hosting this application — each inherits its own transparency grade.
EU AI Act Provider Information
Get insights into risk by running assessments on this AI application.
Work at READ-COOP? Claim this listing to correct or complete the data.
Ready to manage AI applications?
Track, assess, and govern your AI applications with Anove.