In-place OCR + Translate for Internet Archive books

There are lots of OCR tools and translator tools, but using them on books is very laborious, involving downloading images, lots of copying, window-swapping, 3rd-party software, and general dreck. Often the OCR has to be chained to the tranlation, leading to more labor.

I often want to read books in the Internet Archive in languages I don’t speak (e.g. old books in Latin). So I built Bookxlate, a Chrome extension that uses the Google Gemini API to OCR and translate on the fly. Internet Archive transcriptions are notoriously inaccurate, and in any case do not provide translation. This extension just “lets you read the book,” right in your browser, no downloading, window swapping, and so on.

You need to provide a Google Gemini api key, which you can obtain here: https://aistudio.google.com/apikey

Source code here: https://github.com/viking2917/xlate, blog post here: https://www.viking2917.com/translating-internet-archive-book....

The code is generated mostly by Claude, and the translations by Gemini, so…caveat emptor.