HHS · no agency ID · record R0999

AWS Exscribo

Department of Health and Human Services · HHS/NIH

Overview

Development stage: PilotSource: b) Pilot – The use case has been deployed in a limited test or pilot capacity.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2025-01 (month precision)Source: Jan-25
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Administrative Functions
Operational functions: Translation and transcription Derived by keyword rules; see methodology

Problem the AI is intended to solve

Typical transcription services struggle to handle scientific and biomedical terminology, and many platforms do not include the ability to pretrain for specific words, or offer the ability to perform queries on that text in the transcription system itself.

Expected benefits

The AWS Exscribo application is specifically built to allow for custom vocabularies, editing of meeting transcriptions, and model retraining, making it well-suited to handle complex medical terminologies. It also has the benefit of using AWS Bedrock, which enables Gen AI prompting on the transcription.

System outputs

The AI systems output includes transcriptions of audio recordings, and outputs of results from Gen AI prompts on those transcriptions.

Technology

AI classification: Generative AISource: Generative AI: AI that generates new or synthetic content (e.g., images, videos, audio, text, code).
System name(s): Not reported
Custom-developed code: Yes
Public source code: github.com ↗

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): Deloitte, AWS
Vendors (standardized): Amazon Web ServicesDeloitte

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: No
Demographic features: k) None of the above
Training and evaluation data: Custom Vocabularies of words or acronyms that are important to conversations, and any edits that are made to the output of the transcription that are used for training.
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported