speech-to-text

or speech to text

[ speech-tuh-tekst ]

noun

, Digital Technology.

1. a computerized, algorithmic process that transcribes a user’s spoken input into digital text, such as a video transcript rendered by auto caption (often used attributively): Speech-to-text technology showed a bias toward certain mainstream accents and dialects in its speech recognition. : STT

   Speech-to-text is a great way to send a text when you are driving and can’t pick up your phone.

   Speech-to-text technology showed a bias toward certain mainstream accents and dialects in its speech recognition.

Word History and Origins

Origin of speech-to-text¹

First recorded in 1980–85

Example Sentences

That’s what academic researchers concluded in a recently published analysis of Whisper, an AI-powered speech-to-text tool developed by OpenAI, which can be used to transcribe medical discussions or jailhouse conversations monitored by correction officials.

From Los Angeles Times

“Doctors are using speech-to-text tools to transcribe patient notes,” says Allison Koenecke, a computer scientist at Cornell University and lead author of the study, which was posted as a preprint to arXiv in February.

From Science Magazine

“No speech-to-text system is able to model all this variability in articulation and pronunciation to a good level yet,” she says.

From Science Magazine

The large AI models work well: Their transcriptions are more accurate than other speech-to-text tools that rely on small-scale language models.

From Science Magazine

“Not only because of potential hallucinations,” she says, “but also because all speech-to-text transcription systems make transcription errors.”

From Science Magazine