Amazon Transcribe: Getting Started

Transform speech into searchable text with Amazon Transcribe

Discover how Amazon Transcribe uses automatic speech recognition (ASR) to convert spoken audio into accurate, searchable text, helping organisations improve accessibility, automate workflows, and extract insights from audio content.

Apply speech recognition to real-world transcription workflows

Explore Amazon Transcribe’s core features, pricing, and scalable architecture while following a guided hands-on demonstration to create batch and real-time transcriptions, building practical knowledge of AI-powered speech-to-text solutions.

You’ll access learning content and practical activities online through Amazon Web Services (AWS), alongside your FutureLearn course experience, giving you direct access to AWS learning as you progress.

This course is ideal for developers, architects, cloud professionals, and anyone interested in speech recognition and transcription services on AWS.

This course is ideal for developers, architects, cloud professionals, and anyone interested in speech recognition and transcription services on AWS.

• Understand how Amazon Transcribe works
• Familiarize yourself with basic concepts of Amazon Transcribe
• Recognize the benefits of Amazon Transcribe
• List typical use cases for Amazon Transcribe
• Describe the typical architectures associated with an Amazon Transcribe solution
• Specify what it would take to implement Amazon Transcribe in a real-world scenario
• Understand the cost structure of Amazon Transcribe
• Implement a demonstration of Amazon Transcribe in the AWS Management Console