New course · Session 3 — Practical LLM productivity goes live this FridayJoin the community →Webinar · Clinic Systems 1.0 — invoice, token & stock toolsSave your seat →We build · Custom AI tools for your clinic, with your name on itTell us what you need →New course · Session 3 — Practical LLM productivity goes live this FridayJoin the community →Webinar · Clinic Systems 1.0 — invoice, token & stock toolsSave your seat →We build · Custom AI tools for your clinic, with your name on itTell us what you need →New course · Session 3 — Practical LLM productivity goes live this FridayJoin the community →Webinar · Clinic Systems 1.0 — invoice, token & stock toolsSave your seat →We build · Custom AI tools for your clinic, with your name on itTell us what you need →New course · Session 3 — Practical LLM productivity goes live this FridayJoin the community →Webinar · Clinic Systems 1.0 — invoice, token & stock toolsSave your seat →We build · Custom AI tools for your clinic, with your name on itTell us what you need →New course · Session 3 — Practical LLM productivity goes live this FridayJoin the community →Webinar · Clinic Systems 1.0 — invoice, token & stock toolsSave your seat →We build · Custom AI tools for your clinic, with your name on itTell us what you need →New course · Session 3 — Practical LLM productivity goes live this FridayJoin the community →Webinar · Clinic Systems 1.0 — invoice, token & stock toolsSave your seat →We build · Custom AI tools for your clinic, with your name on itTell us what you need →
← All projects
AIVoiceDocumentationPrivacy

Voice Lens

Local AI transcription system that converts doctor conversations into structured medical notes without sending recordings to cloud.

Cover image — drop one in /public/images/projects and set "cover"

Overview

Voice Lens removes typing burden during consultations while keeping patient conversations private and ready for clinical documentation.

Features

Local transcriptionRuns on local hardware for privacy.
Structured notesConverts speech into medical format.
Speaker recognitionSeparates doctor and patient voices.
Multiple AI providersSupports browser and cloud adapters.
ExportCopy notes into WHIMS instantly.

Screenshots

Updates

2026-07-12
v1.2 — Structured output

Better clinical formatting.

2026-06-30
v1.1 — Multi-provider support

Added adapter architecture.

2026-06-20
v1.0 — Initial release

Local transcription system.

Documentation

Full setup notes and the source live on GitHub. Open the documentation →

Want help setting it up?

Bring your questions to the WiseAitechs community — the Discussion channel is where setup help happens.

Join the community