• We're currently having issues with our e-mail system. Anything requiring e-mail validation (2FA, forgotten passwords, etc.) requires to be changed manually at the moment. Please reach out via the Contact Us form if you require any assistance.

Prism's tacotron2 tts banks *WIPs*

Prism

Enthusiast
Jul 18, 2019
525
Oh no..... The voice bank didn't come out well for 8 hours of training maybe the voice isn't a good fit.
 

Prism

Enthusiast
Jul 18, 2019
525
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.
 

Nokone Miku

Aspiring Lyricist/Producer
Jul 14, 2021
76
www.youtube.com
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!")

What about reaction noises like: "un-hn, yep" ; "ah! that's right." ; "aah, I see." ; "huh?" ; "ooh." ; "oh!" ; "wha?" ; "oh no." ; "augh" ; "uwah!" ; "(gasp)" ; "hey!" ; "woo~!"
 

Prism

Enthusiast
Jul 18, 2019
525
No reaction noises that aren't real words or laughs. Is there a reason why you would want that? Also japanese voices are still only in japanese.
 

Nokone Miku

Aspiring Lyricist/Producer
Jul 14, 2021
76
www.youtube.com
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.
 

Users Who Are Viewing This Thread (Users: 0, Guests: 1)