Back to Catalog
Machine Learning

Amazon Transcribe

"Automatically convert speech to text."

Amazon Transcribe

Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capabilities to their applications.

Key Features

  • Speech-to-Text: Converts audio files or streaming audio into text.
  • Speaker Identification: Can identify different speakers in an audio file (Speaker Diarization).
  • Custom Vocabulary: Improve accuracy for domain-specific terms (names, technical jargon).
  • Automatic Language Identification: Detects the dominant language in the audio.
  • PII Redaction: Can automatically redact Personally Identifiable Information from transcripts.

Exam Tips

  • "Speech to Text": Answer is Transcribe.
  • "Subtitles / Captions": Answer is Transcribe.
  • "Speaker Identification": Unique feature of Transcribe.

Common Use Cases

  • Meeting Notes: Transcribing recorded meetings.
  • Subtitles: Generating subtitles for videos.
  • Customer Service: Transcribing and analyzing customer support calls.
AWS Support Plans
Polly
SWIPE ZONE
< DRAG ME >