I assumed unity.cpp would be on feature parity with the original engine, but looks like it only generates the translated text, and not the audio.
Is this something that will be made available in the future? Or should we be just using a 3rd party tts system to feed the translation in and get the audio?
Thanks for your interest. ATM, unity.cpp only supports the text decoder. Our goal is to implement the full model, but speech generation is a bit more complicated than text generation.
I assumed unity.cpp would be on feature parity with the original engine, but looks like it only generates the translated text, and not the audio.
Is this something that will be made available in the future? Or should we be just using a 3rd party tts system to feed the translation in and get the audio?