What Is STT? Speech-to-Text Definition
STT (Speech-to-Text) is the conversion of spoken audio into written text, used interchangeably with ASR (Automatic Speech Recognition).
Definition
STT (Speech-to-Text) is the conversion of spoken audio into written text, used interchangeably with ASR (Automatic Speech Recognition). Powers captioning, transcription, and dictation.
Also known as: Speech-to-Text
Full Explanation
STT (Speech-to-Text) is the conversion of spoken language audio into written text. The terms STT and ASR (Automatic Speech Recognition) refer to the same technology and are used interchangeably, 'STT' is more common in product and API contexts (e.g. 'Google Cloud STT'), while 'ASR' is more common in academic and engineering contexts. Modern STT services like OpenAI Whisper, Google Cloud Speech-to-Text, Microsoft Azure Speech, Deepgram, and AssemblyAI are commonly used as the backend for caption generators, podcast transcription tools, voice assistants, and dictation software. Quality differs across: language and accent coverage, word-level timing granularity, latency (real-time vs batch), and price per audio minute.
Examples
- -Calling Google Cloud's STT API to transcribe a podcast.
- -The Whisper Python library converting an MP3 to a transcript.
Related Terms
Frequently Asked Questions
Everything you need to know before you start.
Can't find what you're looking for? Contact us