OCR Supreme

By VDS Ltd | Updated a month ago | Visual Recognition

8.4 / 10



Service Level


OCR Supreme Overview

Followers: 5
Terms of use
API Creator:
Rate API:
Log In to Rate API


Powerful optical character recognition - 24 languages - supporting all common image formats and multiple output formats, including PDF (with selectable text overlay), HTML (hOCR) and plain text.

Feel free to send us a message if you are having issues.

Perfect for a wide range of applications including automatic transcribing of scanned pages, invoices, identity documents and more.

Current supported languages;
English, Arabic, Bulgarian, Chinese (Simplified), Chinese (Simplified)(Vertical text), Chinese (Traditional), Chinese (Traditional) (Vertical text), Croatian, Czech, Danish, Dutch, Finnish, French, German, Greek, Hungarian, Korean, Korean (Vertical text), Italian, Japanese, Polish, Portuguese, Russian, Slovenian, Spanish, Swedish, Turkish

Multiple languages can be selected for images with two or more languages present.

Please ask if your desired language isn’t listed and we’ll see if we can add support.

Supported languages are spread across two endpoints, call the list languages endpoint to see which language is accessible from each endpoint.

Currently supported input file-types;
TIFF, JPEG, PNG, GIF, WebP - (PDF coming soon).

There is a 7MB max file size and the API is currently limited to a 30 second request time. This is more than enough for most use cases. The larger the file and the more text there is, the longer the processing and response time will be. To ensure we can reliably transcribe your images, please test with your most challenging input (file size and character count) to ensure this service is right for your needs.

An endpoint that will support very large payloads is under development.

Currently supported output types;
PDF (of the supplied image with selectable & searchable text overlay)
HTML (hOCR bounding box and text position data)
Plain Text

Rating: 5 - Votes: 1