Hi, I was looking for a C++ library for use as stated in the title. I was considering using Voce; however, for the project, I wanted to be able to use a custom voice. For example, in most TTS programs you can pick voices. I wanted to record a custom one. However, I don't really know how these libraries work internally, and since the text to speech is referred to as synthesis, it seems they are created through algorithms rather than recordings. Is there any library which I could use a custom recorded voice with? Sorry if this is a stupid question.
I don't think there are any speech tech providers that offer custom TTS voice options yet. I know iSpeech is coming up with voice cloning though. They have a cloud TTS api (http://www.ispeech.org/api) to integrate their voices into any app/platform. Hopefully voice cloning will be added to the api as well.
Alright, thanks. I think I might try using a speech-to-text app and have that text open specific audio files in succession. Not really sure how it would work since I would have to record every possible word. Anyway, thanks!