
Amazon Transcribe is an AWS service that turns audio files and audio streams into text using machine learning. It is used through an API or the AWS command line.
APIUsage-based
Step 1: Create an AWS account.
Step 2: Read the Amazon Transcribe Developer Guide for an overview of the transcription features.
Step 3: Pick the guide that fits your audio: general, Medical, Call Analytics or HealthScribe.
Step 4: Call the service through the API using the sample requests in the API Reference, or through the AWS CLI.
Step 5: Check the error descriptions in the API Reference when a request fails.
It transcribes audio files and audio streams into text.
Yes. The documentation has separate guides for Amazon Transcribe Medical and Call Analytics, plus AWS HealthScribe for clinical notes.
Use the API, documented with sample requests and responses, or the AWS CLI, which has its own command reference.
AWS HealthScribeAWS HealthScribe applies AI to generative AI healthcare API for transcribing patient-clinician conversations and producing preliminary clinical documentation.
Amazon PollyAmazon Polly applies AI to neural text-to-speech service for generating spoken audio in applications, accessibility, and media workflows.
Amazon TextractAmazon Textract applies AI to machine-learning document extraction API for text, forms, tables, queries, invoices, and identity documents.
Cartesia VoiceCartesia provides real-time voice AI through one API: text-to-speech, speech-to-text and managed voice agents for phone calls. Speech is supported in 44 languages.
AssemblyAIAssemblyAI is a voice AI platform with APIs for speech-to-text, text-to-speech, speech understanding and LLM access. Developers use it to build voice agents, notetakers and call analytics.