OCR API

Quickly and accurately convert any image-based document into an editable text file or searchable PDF. The RESTful API detects and extracts text from images to collect and store the content without having to re-type or manually enter data. Compatible with PDF, JPG, TIF, PNG, and BMP. This is available for cloud users and as an add-on for self-hosted users.

Features:

  • 41 languages supported
  • Automatically detect page orientation
  • Check extraction results using confidence values returned with each character
  • Compatible with various page layouts, including interspersed photos and graphics within text
  • Image-over-text PDF output has searchable text that aligns with the text on the image, and adjusts for varying font sizes on the page

Test the OCR API input and output using the demo below or view the documentation for details.

Start your 30-day free trial


step 1. choose output type:

Select your desired output format. Cloud OCR will extract the text detail from your scanned image and provide you with results as either a plaint text document or in a searchable PDF format.

step 2. choose a test file:

Choose one of the files below. Please note that currently we are only supporting .jpg, .tif, .png, and .bmp files for OCR.



Click on the dropdown menu below to select your demo of interest.