search

rhasspy / piper

A fast, local neural text to speech system
https://rhasspy.github.io/piper-samples/
MIT License
6.06k stars 441 forks source link

names of voices #499

Open willwade opened 4 months ago

willwade commented 4 months ago

I'm working on a bunch of new aspects to TTS-Wrapper - a wrapper library around quite a few online TTS systems

https://github.com/willwade/tts-wrapper/tree/piper-tts

Largely commercial systems. The wrapper makes it all a bit easier to write a unified TTS system. It works alongside https://github.com/willwade/py3-tts - which is largely on-device TTS (SAPI, NSS, espeak (although espeak broken IMHO).

anyway we have a get_voices call - which is nice as piper has a similar method. But am I missing something about the name of the voices?

In https://github.com/rhasspy/piper/blob/master/VOICES.md - we have names - but Im not seeing that in the upstream json https://github.com/rhasspy/piper/blob/master/src/python_run/piper/voices.json (or the one on huggingface)

synesthesiam commented 4 months ago

Cool project, especially the SSML support!

A more up-to-date JSON file is here: https://huggingface.co/rhasspy/piper-voices/blob/main/voices.json