I am trying to find information about how the speechSynthesis voices work in the Web Speech API. I understand how to use them, but I cannot find any information about how the individual voices actually work. What kind of architecture is under the hood?
Does anyone know of any documentation on the voices populated by the Web Speech API? From what I've found, they are browser/operating system dependent, but I can't find an example of how a single one actually operates. I'd be happy to find any, but am particularly looking for information on the "Google UK English Male/Female" and "Google US English" voices.
I've read through the Web Speech API documentation and what I believe to be the relevant portions of the Chromium source code. I've googled a ton and asked GPT4 - but cannot for the life of me find the actual information about how these are working.
Appreciate any help/ideas of how to find this information!