Surya logo

Surya

A local OCR toolkit with layout analysis, reading order and table recognition in 90+ languages.

FreeOpen sourceCommand line
Official websitegithub.comDownload pagegithub.com

These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.

About Surya

Surya is a 650M parameter OCR model with command-line tools that extract text from document images and PDFs on your own machine. Besides text recognition, it detects layout elements such as tables, images and headers, works out reading order and recognises table rows and columns.

It covers more than 90 languages. Smaller models are included for line-level text detection and OCR error detection. Datalab also offers a paid managed platform, but the models run locally without it.

Strengths

  • Layout analysis and reading order alongside OCR
  • Table recognition with rows and columns
  • Supports more than 90 languages

Limitations

  • Model weights are under a separate licence from the code
  • Runs best with a capable GPU
  • Command-line and Python use only

Details

Pricing
FreeThe code is free under Apache 2.0; model weights have a separate licence and Datalab sells a hosted platform.
License
Apache-2.0
Developer
Datalab
Platforms
Command line
How it runs
Downloadable app
Account
Not required
Works offline
Yes
Best suited for
Extracting text and structure from scanned documents locally
Last verified
Added

Alternatives to Surya

Compare all

Software that can replace Surya for an important use case, and what changes if you switch.

  • olmOCR

    Open-source toolkit that uses a vision language model to turn PDFs and scans into Markdown.

    FreeOpen sourceLinuxCommand line

    olmOCR uses a vision language model to turn PDFs and scans into Markdown, handling tables, equations and handwriting, with open Apache-licensed model and training code.

  • MinerU

    A document parser that converts PDFs, Office files and scans into Markdown and JSON.

    FreeProprietarySelf-hostedCommand line

    MinerU parses PDFs, Office files, EPUB and scans into Markdown and JSON with OCR, but uses a non-standard license and suits technical users.

  • Docling

    Open source library that converts documents into AI-ready structured formats.

    FreeOpen sourceWindowsmacOSLinuxCommand line

    Docling is an MIT licensed library converting many document formats into structured output, focused on document conversion more than multilingual OCR.

Similar software

Related functionality, not necessarily a direct replacement.

Report a wrong fact or a dead link on this listing