Re: [orca-list] making Linux a hospitable place for TTS engines like Voxin

[Kyle]

I messed around with MaryTTS some years back. I even wrote a little 
interface at one point that would allow the generic sd module to talk 
through it. But I found it to be very cumbersome on most hardware, as it 
had to talk to MaryTTS by sending an http request to the speech 
synthesizer and playing the wav output that was returned. I also have 
found Java to be very very slow overall. There was also a strange 
tendency for MaryTTS voices to suddenly raise their pitch to a very 
squeaky high, although I didn't hear many of the English voices do that. 
I did hear bdl get rather tinny and oldschool at random times however, 
sounding autotuned or like packet loss was occurring in an extreme 
low-bitrate speech recording.


Perhaps work could be done to integrate the already existing RHVoice 
module into sd. I use RHVoice here every day all the time, and it sounds 
smoother and runs with less resources than MaryTTS. It also doesn't get 
tinny or scratchy at random times. I'm not fully sure, but I don't think 
new voices require proprietary tools in order to train them either, 
though I could be wrong about that. In any case, have a look at the 
excellent work over at

https://github.com/olga-yakovleva/rhvoice

~Kyle