I would like to know How can I create a custom voice that can then be used with text to speech synthesizer on MacOS? or is this not possible owing to Apple’s tightly controlled ecosystem? Although pointers to turnkey solutions are accepted, I am more interested in how as a developer I can create a voice font “in-house” using free open-source (or even paid) libraries. By in-house I mean I don’t want to be using cloud services like AWS, Azure, Google for this.