tortoise TTS is too slow and making good AI models takes time
websites like elevenlabs and fakeyou are too expensive for mass production of audio. You can get away with shorter stuff for free, however.
for TTS i still use festival scripts piped through libreoffice writer TTS plugin. I can get Linux or Windows to generate an 10 hour audiobook from a pile of text ripped out of a PDF in about a half an hour. Not bad. problem is, it sounds like shit.
MP3 attached is an example of the kind of output you get from that. I previously made this thread:
https://leftypol.org/tech/res/18106.htmlI often listen to audiobooks because I'm too busy with kids and work these days to really commit with a hard cover book. I can listen to an audiobook when changing a diaper or doing laundry or at work. I can't do that with a regular book. Problem is, not everything I want to listen to has a professionally made audiobook ready for it, and even if it does, I can't always find a good torrent. I still explore TTS pretty often because I think it has a lot of potential for helping people who don't have time to read a regular book. Also visually impaired and blind people.
Do any of you mess around with TTS? If so, what's your approach?