Is the Supertonic TTS model going to be available in Sherpa?

[esconer]

Hello,

I'd like to inquire about the possibility of adding support for a new text-to-speech model: Supertone/supertonic.

The model is particularly interesting because it reportedly offers quality comparable to Kokoro TTS but with a significantly smaller parameter count. This makes it a very promising candidate for on-device inference, and I am hoping to use it on Android via the Sherpa TTS engine.

Are there any plans to integrate this model into Sherpa in the future?

Thank you for your time and consideration.

[rominf]

It is supported now. See the latest release: https://github.com/k2-fsa/sherpa-onnx/releases/tag/v1.12.29