I am looking for a API server that I can host locally and use the voice models for TTS

[harsh arrow]

For a hobby project I require TTS.
I am currently using the docker container from https://github.com/matatonic/openedai-speech
This however uses onnx models and not the models I find in this discord.

Is there a way for me to still use the models I find here and have them run on the openedai-speech image or is there a better solution that I could convert to?

[stray ermine]

Ehh you could download wokaoda and use the export to onnx function, I actually dont know where else to do it

Theres probably a better TTS tool in the first place though, but thats not my area of expertise

[high sonnet]

That would work???

[high sonnet]

RVC has a no ui command line version

You can use edgetts to generate the tts and RVC to convert the voice to a voice in the server

https://github.com/RVC-Project/Retrieval-based-Voice-Conversion

https://github.com/blaisewf/RVC_CLI or applios version