Ok, nice, I understand the point.
About TTS, I've been doing some research, the TTS I need must run locally, be written in C++, multilingual and provide me with audio analysis, i.e. the visemes.
The one I see potentially to use would be this one:
https://github.com/PABannier/bark.cpp
It would be perfect because it is the brother of llama.cpp and whisper.cpp, and it also uses the SUNO AI technology with which I made the music for the video game.
However, it doesn't have, as far as I can see, the audio analysis for the visemes :'(, I'll keep an eye on this project.
(If I could integrate this technology then MTW could run on Windows, Linux and MAC)