Read PDF with Google Cloud OCR

Hello, i am trying to read a pdf file with Google Cloud OCR for extract a table but i need the apikey to make it work.
Does anyone know how to extract it and how to use it? or what is the difference between Google Cloud OCR and Google OCR?(just out of curiosity)

Regards. :slight_smile:

1 Like

Hi Bryan,

The difference is the engine: Google Could OCR is using the Google Cloud OCR engine and Google OCR is using Tesseract OCR Engine.

You have to provide you own API Key. You could register for a free trial here:


Hi Bryan,

Here are some differences between the two engines:

  • Computing location. Google OCR is using the Tesseract engine which is deployed locally (comes with UiPath Studio) and the image processing and text extraction is done locally, on your computer. While Google Cloud OCR is uploading the image to be processed to Google server (cloud) and you get back the resulting text. So all the processing is done remotely on Google servers and you just get the result.
  • Accuracy: Google Cloud OCR returns better results in most cases.
  • Cost: Google OCR is free while you need to pay for Google Cloud OCR (free trial is available with limitation)

Thanks, it worked :smile:


where did you get ApiKey after registering here

could you please share me any screenshots

Hello @Darkbrix,
Could you please share your *.xaml files of your sample?

Many thanks,


And, please be collaborated showing me steps to make it worked? Is it possible to use screen record function (Screen Scraping) to create workflow which invoke Google Cloud OCR activity?

Appreciate your help!