I think it's more worth than ever. The idea that some of my thoughts might be integrated into some AI model by being used as training data is exciting

Coqui is great, but another fantastic tool for TTS I recommend checking out is Piper. The voice quality is great, it's extremely lightweight, and it's fast enough to generate TTS in realtime https://github.com/rhasspy/piper

Can you suggest (1) How to get it working on a Mac, (2) alternatively, how to get it running in a Docker container (on a mac)?

Works with rhel9 docker image and compiled binary link

Thank you!

Piper seems very interesting, but unfortunately the last time i tried it on macOS it didn't seem to work (anymore).