Glossary
Prosody
The rhythm, stress, and intonation of speech — the qualities that make a voice sound natural rather than flat. Conversational recordings carry richer prosody than scripted reads.
Prosody covers pitch movement, timing, loudness, and pausing — how a sentence is performed rather than what it says. TTS trained only on read speech tends toward flat, newsreader delivery; conversational recordings carry laughter, hesitation, emphasis, and turn-taking rhythm. Models mostly learn prosody implicitly from natural speech, since explicit prosody annotation is rare.
Why it matters
Expressive, spontaneous recordings supply the prosody that scripted studio sessions cannot.