Amazon Transcribe
#202 · Level 3 · Modern architecture · AI and machine learningConcept
Section titled “Concept”Amazon Transcribe listens to speech and turns it into text (speech to text). This is called Automatic Speech Recognition (ASR). It can turn pre-recorded audio files into text, and it can also write down live speech as it happens. It can separate who is speaking when, and it can improve accuracy with a list of special words (custom vocabulary). It also has special versions for call centers and for medical use.
Simple example
Section titled “Simple example”A meeting note-taker who writes down everything that is said.
Why it’s needed
Section titled “Why it’s needed”Listening to hours and hours of recordings and writing them down takes a lot of time.
Where it’s used
Section titled “Where it’s used”Call center conversations, video subtitles, meeting notes.
Azure equivalent
Section titled “Azure equivalent”Azure AI Speech (speech to text)
Learn more
Section titled “Learn more”For details and the latest information, see the official documentation: