Comment by _flux
1 day ago
I tried it, and I'm sure it's not a based on any language model. Sounds like espeak-ng or its ilk, so it probably uses whatever's available?
The TTS repo was updated 5 years ago and links to installation instructions for Ubuntu are broken :/. Also the docker repo is archived, but only recently, so maybe it works.
All in all, doesn't look like the project is alive at all.
It definitely uses whatever is available, but on review of the models (and there are quite a few) the ones I checked included instructions for integrating into linux speech engines.
What your distro uses by default might be espeak-ng, but you could use mozilla TTS or festival or piper or anything else. It makes sense to not bundle an entire system that repeats things that are available on all desktop environments and mobile these days, but instead call out to those from the browser functionality - especially given the enormous size of high quality speech models - not to mention the localisation issue. I think the TTS project was just to increase availability of high quality FOSS alternatives. Getting those into your distro is more of a distro packager thing.