LLM-enabled voice interface

Speak to your
medical imaging viewer.

SCRIBE is a voice-driven assistant layer for medical imaging viewers. Dictate structured reports and control your viewer hands-free — powered by a shared speech pipeline and LLM command interpretation.

Join our waitlist → See how it works
01 / DICTATION

Medical dictation

Structured, high-accuracy transcription tuned for medical terminology and reporting workflows — built on research into the MedASR speech-to-text model.

02 / CONTROL

Commands to viewer

Navigate images, adjust views, and trigger viewer actions by voice or text. Natural language is interpreted by an LLM and executed live in your imaging viewer.

The pipeline

From spoken command to executed action

A modular base extension lets any viewer plug into one shared speech pipeline.

{{ st.tag }}
{{ st.label }}
{{ st.desc }}
Integrations

Works across open-source viewers

SCRIBE ships as a shared base extension. Viewers plug into the same pipeline through lightweight adapters.

{{ v.name }}
{{ v.status }}
{{ v.note }}

Be first to give your viewer a voice.

Join the waitlist for early access, integration updates, and pilot opportunities.

You're on the list — we'll be in touch.
{{ error }}