Audio recognition from video

Job ID: 31492772

Budget: $250 – $750 USD

I need a desktop application which can recognize and bleep out swear words from netflix or youtube video.
you can download and test similar one from https://nofanity.com/
but instead of muting, it should just bleep.
It has to be fast and customisable as well, like user should be able to add more keywords to be bleeped out.
I want to develop it as desktop app, not sure needing python, ML, AI, NLP.