Hi folks,

I'd like to give more life to the output of text-to-speech services that produce WAV or MP3 files from lines of text. There would be five to ten such phrases or short sentences per music project. Ideally, I'd like to imprint them with my own intonation and pacing while keeping the general character of the synthetic voice. I'm guessing mainstream samplers like Kontakt have some useful tools for such manipulation. But, I was wondering if CSOUND had anything more specialized to offer. This seems like a classic analysis --> resynthesis problem, right? Are there any tools for working with speech specifically?

-d. vyd

Csound mailing list
Csound@listserv.heanet.ie
https://listserv.heanet.ie/cgi-bin/wa?A0=CSOUND
Send bugs reports to
        https://github.com/csound/csound/issues
Discussions of bugs and features can be posted here