text-to-speech

American  

[tekst-tuh-speech] / ˈtɛkst təˈspitʃ /

Or text to speech

noun

Digital Technology.

1. a computerized, algorithmic process that converts digital text to audio output resembling human speech, such as the audio generated by screen readers (often used attributively): The updated text-to-speech software allows users to choose among four different voices and vary the speed of the synthetic speech. TTS

   Readers with dyslexia sometimes read in tandem with text-to-speech for improved comprehension.

   The updated text-to-speech software allows users to choose among four different voices and vary the speed of the synthetic speech.

---

Etymology

Origin of text-to-speech

First recorded in 1960–65

Example Sentences

She fed her script into a text-to-speech model and selected a female AI voice from ElevenLabs to speak for her.

From Los Angeles Times

But the multiplayer shooter has been criticised for using text-to-speech tools to create additional lines, based on dialogue previously recorded by the game's actors.

From BBC

While the game contains traditional recorded performances, the actors involved also gave permission for their voices to be used as training data for text-to-speech models.

From BBC

Using a text-to-speech system, users can type anything and Iona will speak it out loud in a Scottish accent.

From BBC

The artists, a couple living in New York City, filed a proposed class action lawsuit in 2024 after learning alleged clones of their voices were for sale via Lovo's text-to-speech platform Genny.

From BBC