Thought it might be good to post more here Luka ai tts is in development and has 5 banks 2 mature and 3 high. They use a small amount of data like less than 10 minutes so I might combine them to get higher quality. If she is susscesful I will work on rin. I know where I can find samples for her it's just getting them and processing them it very time consuming. I also have data for other. My goals are to make a big project using them.
If we combine a bunch of your TTS banks and a good quality room reverb plugin do you think it would be possible to make the sound of a bunch of people chatting in a large room or hall? Like make up a bunch of conversations and use the plugin to position them at different distances/positions from the "listener."
Is it possible to make them laugh? Or cheer? Or chant? ("Encore! Encore! Encore!")
I often look through free stock sounds for crowd noises of various types. There's a big commercial pack that would probably have everything I could ever want, but it's like $500. It would be cool to be able to make my own custom crowd noises.
The reaction noises would be to punctuate the overall chatter with exclamations and reactions to make everything sound more organic and random.
If the crowd is big enough they could all be saying the Japanese equivalents of "blah blah blah" "yak yak yak" because you can't make out what a large crowd is saying anyway.