What Is Amazon Transcribe Medical?

Amazon Transcribe Medical is an automatic speech recognition (ASR) service that enables you to add medical speech-to-text capabilities to an application. Amazon Transcribe Medical is a Health Insurance Portability and Accountability Act of 1996 (HIPAA) compliant service and is available through either real-time streaming or asynchronous API calls. To help with security and compliance, Amazon Transcribe Medical operates with a shared responsibility model. AWS is responsible for protecting the infrastructure that runs Amazon Transcribe Medical and you are responsible for the management of your data. For more information, see https://aws.amazon.com/compliance/shared-responsibility-model/

Use Amazon Transcribe Medical to transcribe medical-related speech found in a variety of use cases. Example uses include physician-dictated notes, drug safety monitoring, telemedicine, or physician-to-patient conversations.

Use Amazon Comprehend Medical for further analysis of your transcript.

Important Notice

Amazon Transcribe Medical is not a substitute for professional medical advice, diagnosis, or treatment. Identify the right confidence threshold for your use case, and use high confidence thresholds in situations that require high accuracy. For certain use cases, results should be reviewed and verified by appropriately trained human reviewers. All operations of Amazon Transcribe Medical should only be used in patient care scenarios after review for accuracy and sound medical judgment by trained medical professionals.

Streaming Audio Transcription

Amazon Transcribe Medical enables you to transcribe medical speech in real time. To do this, use a WebSocket protocol to establish a bi-directional connection to the Amazon Transcribe Medical real-time application programming interface. When you send Amazon Transcribe Medical a stream of audio, it returns a stream of JSON objects containing the audio's transcription.

For more information about processing audio streams, see Establish a Bi-Directional Connection Using the WebSocket Protocol.

API Batch Transcription

Amazon Transcribe Medical supports the transcription of individual audio files through asynchronous API batch calls. For more information about transcribing audio files, see How Amazon Transcribe Medical Works

Batch transcription can improve your transcription results. You can also use channel identification to separate and transcribe channels in audio files that have multiple channels. Channel identification generates separate transcripts for each channel and merges them into a single output. To identify speakers in single-channel audio files, use speaker identification. To generate additional alternative transcription results for the same source audio, use alternative transcriptions.

Supported Specialties

Amazon Transcribe Medical supports transcription for PRIMARYCARE, which includes the following specialties:

• Family medicine

• Internal medicine

• Obstetrics and Gynecology (OB-GYN)

• Pediatrics

Are You a First-time User of Amazon Transcribe Medical?

If you are a first-time user, we recommend that you read the following topic to get an introduction to Amazon Transcribe Medical: How Amazon Transcribe Medical Works.