A proof of concept which takes a PDF and creates a translated version of the document. It uses JPedal to read the original text, call Translator and then replace the original text using JPedal's annotations feature.
This project demonstrates how to extract text as paragraphs from PDFs, translate them using a language translation API, and reinsert the translated content back into the document as an overlay to the original content.
This is achieved using our Java PDF toolkit JPedal to extract the text from the document, and write the annotations back to the file.
The content translation can be done with any library. We chose to use Translator.
Copyright 2026 IDRsolutions