AWS HealthScribe

Automatically create clinical notes from patient-clinician conversations using generative AI

Why AWS HealthScribe?

Transform the patient-clinician experience with conversational and generative AI

AWS HealthScribe is a HIPAA-eligible service empowering healthcare software vendors to build clinical applications that use speech recognition and generative AI to automatically generate preliminary clinical documentation.  

Using a single API, AWS HealthScribe automatically identifies speaker roles, classifies dialogues, extracts medical terms, and generates rich preliminary clinical transcripts and notes. AWS HealthScribe removes the need to integrate and optimize separate AI services, allowing you to expedite implementation. Powered by Amazon Bedrock, AWS HealthScribe makes it faster and easier to integrate generative AI capabilities, without needing to manage the underlying machine learning (ML) infrastructure or train healthcare-specific large language models (LLMs).



Transcribe patient visits, generate preliminary clinical notes, and extract insights that help clinicians to quickly revisit highlights of their patient visits and easily accept, reject, or edit content suggestions.
Every AI-generated summary statement comes with traceable transcript references that make it easier for clinicians or scribes to quickly verify accuracy and locate the source of the insight.
Simplify implementation with an integrated conversation and generative AI service that is specifically trained for the healthcare industry.
Built with security and privacy in mind, you control where your data is stored, with data encrypted in transit and at rest. AWS does not use inputs or outputs generated through the service to train its models.

Data on the clinical documentation burden


Physicians report excessive documentation leading to burnout


The amount of time spent by clinicians on administrative tasks than with patients


Patients report had a negative patient experience

Features of AWS HealthScribe

AWS HealthScribe uses generative AI to transcribe and summarize patient-physician conversations—freeing up more time for patient care instead of documentation.  

Use summarized clinical notes

AWS HealthScribe analyzes consultation conversations to generate summarized clinical notes for sections like chief complaint, history of present illness, assessment, and treatment plan. You can provide these summaries in your clinical application to help clinicians and medical scribes quickly recap highlights of patient visits and review, edit, and finalize notes for clinical documentation.

Extract structured medical terms

AWS HealthScribe extracts structured medical terms, such as medical conditions, medications, and treatment from the conversation transcript. You can use these medical terms in your clinical application to generate useful workflow suggestions for the user. Medical terms can be used to auto-suggest relevant reading material or entries for a drop-down form in your application.

Generate rich consultation transcripts

AWS HealthScribe provides a rich turn-by-turn transcript with word-level timestamps. AWS HealthScribe also identifies speaker roles, like patient and clinician, for each dialogue in the transcript.

Segment transcripts

AWS HealthScribe segments transcript dialogue into categories such as small talk, subjective, and objective, based on the dialogue’s clinical relevance. Categories can be subsequently used to help locate specific portions of the transcript.

Validate outputs with evidence mapping

Every sentence in the AI-generated clinical note includes references to the original consultation transcript, making it easier for users to validate the accuracy of the summary. Providing traceability and transparency for AI-generated insights is consistent with Responsible AI’s principle of explainability. Sharing references along with the summary notes to clinicians or medical scribes helps foster trust and encourages safe use of AI in clinical settings.

Eligible for HIPAA compliance

AWS HealthScribe is a HIPAA-eligible service that prioritizes security and privacy for patient data. The service does not retain inbound audio or output text, nor does it use your data to train AI models. You have full control to determine whether to store transcripts in local environments or self-managed cloud storage.