ChunkyMonkey
Audio

Text-to-Speech (TTS)

Synthesizing natural-sounding spoken audio from written text — the engine behind AI voiceovers.

Text-to-speech converts typed text into spoken audio using AI voices. Modern TTS is expressive enough to narrate explainers, power avatars, and voice faceless content without a recording session. You can usually choose voice, accent, pace and tone.

Paired with voice cloning, TTS can speak in your own voice, or in many languages for localized versions.

AI voices (soon)

Related terms

Keep reading.

← Back to the full glossary

Stop reading, start posting.

Turn a long video into ranked, captioned clips — free to start.

Start free →
Free plan · Cancel anytime
Ready