Kraken
kraken.re
- Free plan
- macOS
- Linux
- API
What Kraken is
Kraken is a free, open-source automatic text recognition system for historical documents, humanities digitization, and non-Latin or low-resource writing. It runs on Linux and macOS, including x64 and ARM systems, with Python 3.10 through 3.13. A customizable command-line interface and Python API support tailored workflows and integrations. Kraken provides trainable layout analysis, reading order, and character recognition, including right-to-left, bidirectional, and top-to-bottom scripts. Results can include word bounding boxes and character cuts, with output in ALTO, PageXML, abbyyXML, or hOCR. Processing requires a model, and documentation recommends one trained on similar material; a public repository supplies freely available models. The API includes segmentation, recognition, and forced alignment classes, while plugins can add commands, model types, and tasks. Direct PDF and multi-image TIFF/JPEG2000 input requires the PDF extras package. Integrations include eScriptorium, OCR4all, OCR-D, and arkindex by Teklia.
Who it suits
Kraken is aimed at humanities researchers, digitization teams, and developers handling historical documents or less-supported scripts. Its command-line and Python interfaces suit custom processing pipelines.
Good to know, and what to watch
- Free Apache 2.0 open-source project
- Trainable layout and character recognition
- Supports multiple script directions
- Exports ALTO, PageXML, abbyyXML, and hOCR
- Python API and plugin extensibility
- A model is required for processing
- Similar-material training is recommended
- PDF extras needed for some inputs
- Runs on Linux and macOS only
The verdict
Kraken targets specialized text-recognition work where script direction, historical material, and trainable models matter. Its formats, APIs, and plugin system support custom humanities digitization workflows, provided users supply suitable models.
What the maker publishes
- Configuration
- Kraken supports configurable recognition through a network specification language and a plugin system. source
- Extensibility
- Kraken’s plugin system lets developers add commands, model types, and tasks through Python entry points. source
- Free plan
- Yes source
- Handwriting OCR
- Yes source
- Supported inputs
- both source
- Installation
- The getting-started guide says Kraken runs on Linux and macOS on x64 and ARM, and supports Python 3.10 through 3.13. source
- Installation
- The documentation says Kraken can be installed on Linux or Mac OS X, on x64 and ARM, using pip or Anaconda. source
- Integrations
- The documentation lists eScriptorium, OCR4all, OCR-D, and arkindex by Teklia as applications or suites integrated with Kraken through its API or a plugin. source
- Integrations
- The documentation lists eScriptorium, OCR4all, the OCR-D suite, and arkindex by Teklia as applications or suites integrated with Kraken. source
- Intended users
- Kraken is designed for humanities digitization, including work with low-resource languages and diverse, non-conventional scripts. source
- Interfaces
- Kraken provides a customizable command-line interface and a Python API for custom workflows and integrations. source
- Interfaces
- Kraken provides a customizable command-line interface and an API for building custom workflows and integrating it into other projects. source
- Layout and recognition
- Kraken supports trainable layout analysis, reading order, and character recognition. source
- License and development
- Kraken is provided under the Apache 2.0 License and is developed at Inria and École Pratique des Hautes Études, Université PSL. source
- Model repository
- Kraken provides a public repository of freely available models, accessed through its command-line tools. source
- Model requirement
- Kraken requires a model for document processing, and the documentation says a model trained on similar material performs best. source
- Models
- Kraken provides a public repository of model files through HTRMoPo. source
- Optional input support
- Direct PDF and multi-image TIFF/JPEG2000 support requires installing the PDF extras package. source
- Output formats
- Kraken can output ALTO, PageXML, abbyyXML, and hOCR, and supports word bounding boxes and character cuts. source
- Output formats
- Kraken can output ALTO, PageXML, AbbyyXML, and hOCR. source
- Primary platform
- desktop source
- Product
- Kraken is an open-source, turn-key automatic text recognition system optimized for historical and non-Latin-script writing. source
- Purpose
- Kraken is an open-source automatic text recognition system optimized for historical documents and non-Latin scripts. source
- Python API
- The Python API includes task-oriented classes for segmentation, recognition, and forced alignment. source
Checked against the maker's pages on 5 Oct 2026.