Learn

Prosody: the rhythm and melody of speech

Prosody is the musical layer of speech: where the stresses fall, how the pitch rises and dips, where the pauses go, and how fast the words move. Two voices can say the same words with the same accuracy yet feel completely different because of prosody. It is what separates a living voice from a flat, read-aloud one.

At a glance

What it is
The rhythm, stress, intonation and pacing layered over the words
What it carries
Emphasis, mood, and the difference between a question and a statement
Why it is hard
It depends on meaning and context, not just the letters in the text
How you judge it
Mostly by ear; it resists a single clean number the way WER gives one

How does prosody work?

When a TTS model reads a sentence, getting the words right is only half the job. It also has to decide which syllables to lean on, where the pitch climbs and falls, how long to hold a pause, and how quickly to move. Those choices ride on top of the words and shape how the line lands. A question that ends with a flat pitch sounds wrong even if every word is correct.

Good prosody depends on understanding the sentence, not just spelling it out loud. The model has to infer where the emphasis belongs from meaning and context, which is why the same text can be read a dozen plausible ways. Weak models default to one flat reading; stronger ones vary the rhythm in a way that tracks what the sentence is actually saying.

Why does prosody matter?

Prosody is the layer people actually react to. A voice with perfect word accuracy but no rhythm sounds like a screen reader, and listeners tune out fast. The same content with natural stress and pacing feels like a person talking. For anything someone has to listen to for more than a few seconds, prosody is the difference between usable and unbearable.

It is also the hardest part to score. Intelligibility gives you a clean number, but prosody mostly has to be judged by ear, and what sounds right shifts with context and language. That makes it easy to overlook when you lean only on automated metrics, which is exactly why a model can look strong on paper and still sound dead.

Related terms

← All terms Reviewed: June 2026