Same note, three sounds
Three sounds with the same 220 Hz note. What makes each one sound different is timbre.
Every voice has a note, F0, the frequency at which the vocal folds vibrate. But the note alone does not tell whose voice it is. Timbre does: which harmonics exist above the note and how strong each one is.
The sine has only the note and sounds like a whistle. The vowel has thirty harmonics, stronger where the mouth resonates, and already sounds like a voice. The noise has no note at all: it is the air of an "s". Each person's voice is a unique pattern of harmonics and formants. That fine detail is what a synthetic voice must keep to sound like someone, not like anyone.
Read next
Inside the sound
The same speech seen as an image: time across, frequency up, energy as color.ReadSound as numbers
Before any model, a voice is a list of numbers. Take a close look.ReadA new voice without touching every weight
Low-rank adapters: train under 1% of the numbers and keep the same speed.Read