I am creating a text to speech api, and i would like to give the user options to customize text, this includes a variety of things, one of which is censoring. I want to give the user the option to censor some words, the use can input something like
<censor>this text will be bleeped out</censor>
My TTS will generate the audio for this and i want to bleep out the signal. Does anyone know how that can be achieved? I dont want to use any external files [bleep sounds from files], rather i want to modify the signal so it produces a high pitch bleep, doing it this way ensures that the bleep takes place during the actual time taken to speak the sentence. Anyone knows how that can be done?
