Speech recognition: technology that converts spoken language

Speech recognition is the technology that converts spoken language into text or other forms a computer can use.

Speech recognition is the technology that converts spoken language into text or other forms a computer can use. It is used for dictation, searching audio and creating transcripts. It answers 'what was said', which separates it from voice recognition in the speaker sense, which answers 'who is talking'.

Also searched as "speech recogniser" and "speech recognizer".

What the sources say about speech recognition

  • Wikipedia, Speech recognition. Speech recognition (ASR, speech-to-text) converts spoken language to text; productivity uses include dictation and transcripts; accuracy is usually rated with word error rate; voice recognition in the speaker-identification sense identifies who is talking.

Speech recognition in Autrans

Autrans uses speech recognition on recordings in 24 live languages (en, pcm, yo, ha, ig, fr, es, ar, sw, tw, zu, af, am, ln, sn, so, xh, wo, tn, st, ts, ve, om, pt) and then labels speakers and writes notes on top. The language figures it publishes cover words only.

A worked example of speech recognition

Recognition: the sound of 'Good morning, everyone' becomes the text 'Good morning, everyone'. Speaker recognition is a different question: whose voice it was.

Terms next to speech recognition

  • Automatic speech recognition: Automatic speech recognition (ASR) is the field and the technology that converts spoken language into text a computer can use.
  • Speech to text: Speech to text (STT) is software turning spoken language into written text.
  • Voice recognition: Voice recognition is an ambiguous term.
  • Dictation software: Dictation software types what you say as you say it, usually into a document, using speech recognition.

Questions people ask

What does speech recognition mean?

Speech recognition is the technology that converts spoken language into text or other forms a computer can use. It is used for dictation, searching audio and creating transcripts.

How does speech recognition show up in Autrans?

Autrans uses speech recognition on recordings in 24 live languages (en, pcm, yo, ha, ig, fr, es, ar, sw, tw, zu, af, am, ln, sn, so, xh, wo, tn, st, ts, ve, om, pt) and then labels speakers and writes notes on top. The language figures it publishes cover words only.

Where does this definition of speech recognition come from?

It rests on Wikipedia, Speech recognition, read on 22 October 2026. What each source supports is listed above, next to its link.

Can you give an example of speech recognition?

Recognition: the sound of 'Good morning, everyone' becomes the text 'Good morning, everyone'. Speaker recognition is a different question: whose voice it was.

Related

Start transcribing free

Send Autrans into your next meeting, use it in the room, or upload a recording. Your first 30 minutes are free, given once, and no credit card is needed to start.

Last checked 22 October 2026. How we measure accuracy. Spotted a mistake? Write to hello@autrans.online.