We just released a new version of our OCR application named I2S last week.
I2S is an OCR scanner that practically turn almost any images with human readable characters into text content which is in turn transformed into human voice in your native language & accent.
Once the image data (Book page, magazine, journal, scientific paper, etc.) recognized & transformed into text content, you'll be able to playback that text in your local accent & over 45 languages of your choice plus a built-in translation service to over 75 languages and the ability to generate PDFs on the fly for your output text.
Finally, I2S is powered by the PixLab[1] Machine Vision Rest APIs.
Playstore Link: https://play.google.com/store/apps/details?id=net.symisc.ocr...
(iOS release pretty soon)
App website: https://i2s.symisc.net