Maybe not exactly what you’re looking for but I found this a few weeks ago https://github.com/k2-fsa/sherpa-onnx and I haven’t really seen anyone talk about it
I’ve been using the tts on android for navigation and its way better than rhvoice and espeak.
I did try stt on android and it worked great but I’ve never used stt before so I don’t know how good it is compared to other stt
I’ve used https://github.com/Softcatala/whisper-ctranslate2 before for transcribing English and translating non English audio into srt files and its been pretty good for TV shows for me. Its not perfect but it usually gets me about 95% of the way there