Azure Translator gets the ability to scan and translate PDF documents

Microsoft Wikipedia logo

Microsoft’s Azure Translator is get an important new update which enhances the document translation capabilities of the tool. Specifically, the service can now scan PDFs and translate them. This means that users will no longer need to run their documents through an optical character recognition (OCR) engine to translate them.

Azure Translator has been able to translate documents for about a year. It can translate several documents at once in more than 110 languages. However, the latest update makes the cloud tool even more powerful.

Previously, the translator could only support Word and PowerPoint files. Many users wanted a PDF translation because PDFs also contain images. Microsoft says PDF scanning and translation can do the following:


  • “Identify whether or not the PDF document contains scanned image content,
  • Route PDFs containing scanned image content to an in-house OCR engine to extract the text,
  • Reconstruct translated content as normal PDF text while retaining the original layout and structure.


As mentioned, standard document translation for Word and PowerPoint is available in 110 languages ​​and dialects. PDF translation doesn’t quite have that level of scope, but handles 68 source languages ​​alongside 87 target languages.

Microsoft suggests more are to come.

Above all, users can start using PDF translation immediately without having to modify the code. Additionally, the new feature is offered at no additional cost. This means users of current D3 volume and pay-as-you-go models can use it.

Tip of the day: When using your Windows 10 laptop or convertible with a mobile hotspot, you may want to limit the internet bandwidth used by your PC. In our tutorial we show you how to set up a metered connection in Windows 11 or Windows 10 and how to disable it again, if needed.