Not an NVDA Add-On, that's for sure, but for anyone who wants to add a text layer directly to an image scanned PDF (or PDF that contains text that's somehow not accessible) and save that permanently as part of the PDF file, see my now ancient tutorial:  Using Tracker Software’s PDF-Xchange Viewer to OCR Process Image Scanned PDFs

Still works like a charm, and they have free language packs for something like 20 languages in addition to the 4 that come built-in to their OCR engine as shipped.  It does not, however, language switch.  It's presumed that the document being OCR-ed is in one language.
--

Brian - Windows 10, 64-Bit, Version 21H2, Build 19044  

Constantly insisting on “my rights” with no consideration of “my responsibilities” isn’t “freedom” — it’s adolescence.
     ~ Commenter, Evangelos, in comments for
         America 2022: Where Everyone Has Rights and No One Has Responsibilities,
        New York Times, February 8, 2022