|
You said something about this being considered state-of-the-art TTS; I didn't understand what you were referring to. The main factor in quality of TTS is the voice; like in a person, a well-educated voice pronounces most words correctly and has an appealing accent. Like with a person, you know something about that particular person if you know the person's name. For example, I like the Kindle's female voice; her name is Samantha. I am familiar with her because I bought her voice to use on my Windows computers.
Were you referring to the voice, or something else as being state of the art?
|