mush42 / sonata-nvda

This add-on implements a speech synthesizer driver for NVDA using neural TTS models. It supports Piper
GNU General Public License v2.0
37 stars 8 forks source link

Feature Request: Implement Support for Voicevox Engine #43

Open dangero2000 opened 2 months ago

dangero2000 commented 2 months ago

Voicevox is a Japanese neural TTS engine. The front end of it is an electron app, but it has a back end core that can be integrated into other applications. Piper currently doesn't have any Japanese voices available for use, but Voicevox has many, and the quality is pretty good. We don't have a lot of Japanese voices available for screen readers right now, or at least, not many that can be accessed easily. It'd be great to have access to more. I'll have links for the main Voicevox repository, as well as the Voicevox Core below, though keep in mind the readme is in Japanese and you'll need access to a translator for it.

Voicevox: https://github.com/VOICEVOX/voicevox Voicevox Core: https://github.com/VOICEVOX/voicevox_core