a photo of a man sitting in a classroom taking notes to symbolize the amazon ai service amazon transcribe which converts speech to text

Amazon Transcribe


Amazon Transcribe converts speech to text, by using Automatic Speech Recognition (ASR) technology which is the same underlying technology used by Amazon Alexa. Transcribe can work with multiple languages and speakers and incorporate custom vocabulary provided by the user. Transcribe can be configured to remove sensitive text, such as PII information or swearing.

Video: What is Amazon Transcribe?

This is a 1.43 minute video from AWS that gives an overview of Transcribe’s capabilities.

Key features

  • Punctuation and number normalization, this provides correctly formatted text
  • Streaming transcription for real time transcription
  • Timestamp generation, this enables to precise part of the audio or video to be identified that corresponds to the transcribed text
  • Custom vocabulary, for business specific and niche words and phrases
  • Vocabulary filtering and Automatic content redaction to remove profane words and phrases and sensitive information
  • Recognize multiple speakers
  • Automatic language identification
  • Amazon Transcribe Medical

Use cases

  • Live-call analytics and agent assist
  • Post-call analytics
  • Clinical Documentation
  • Media content subtitling, automatically add subtitles to videos
  • Media intelligence, convert audio content to text for searching and categorizing
  • Digital scribes and court reporters


Similar Posts