เสียงที่ใช้ร่วมกัน

Depends on your definition of natural sounding. My experience isn’t very current so this is just to point out the need for clarity. Kokoro is hard to match in terms of clarity where I’ve never heard it sound like it’s being generated by a computer (static, half formed words, trailing off, awkward silence), but at the same time it’s largely lacking any emotion or variation in how it says stuff…