The Private Scribe
for Professional Interpreters.

A low-latency assistant that runs 100% locally on your computer, transcribing speech in real-time so you can instantly read what was just said. Capture names, technical figures, and complex terminology during live interpretation with absolute data confidentiality.

TerpScribe — On-Device Active Session
[English (Original)]

Good afternoon. We are here to record the deposition of witness Sarah Jenkins. We will start with case number 2026-CV-8849 at 455 Market Street.

[Spanish (Original)]

Buenas tardes. Estamos aquí para registrar la declaración de la testigo Sarah Jenkins. Comenzaremos con el caso número 2026-CV-8849 en 455 Market Street.

[English (Original)]

Please state your full name and outline the technical specifications of the hardware-locked license structure.

Quick Reference Items

Auto-extracted key data points

PROPER NAMES
Sarah Jenkins19:01
FIGURES & NUMBERS
2026-CV-8849Case #
455 Market StreetAddress
TERMS & JARGON
DepositionLegal
● On-Device Private Intelligence Engine
Offline Mode (macOS UUID Bound)

How It Works

1

Begin to Interpret

  • Audio sent to TerpScribe too
  • Offline speech recognition
  • Zero cloud text exposure
2

Roll Back Time

  • Re-read what was just said
  • Live search entire conversation
  • Practically infinite buffer history
3

Anchor Key Terms

  • One click to save essential terms
  • Dynamic color grouping
  • Drag-and-drop sorting

Key Features

An Interpreter's Assistant

It is a live cognitive buffer that runs quietly while interpreting depositions, trials, and hearings. It transcribes speech in real-time, handling rapid pacing, accents, and complex industry terminology to give you a reliable visual reference without breaking your concentration.

Save Key Terms

No more scrambling to write down addresses, case numbers, or names. The app isolates and highlights numerical digits, street addresses, and proper names in your live transcript that you can pin to a sidebar.

Absolute Confidentiality

TerpScribe runs entirely offline to protect client privilege and confidentiality. Audio is processed directly in your computer's temporary memory—no voice files are ever archived on your hard drive, no transcripts are saved, and absolutely no data is sent online, neutralizing data liability from the moment you close the app.

Supported Languages (21)

English, Spanish, French, German, Italian, Portuguese, Russian, Dutch, Polish, Czech, Swedish, Danish, Finnish, Greek, Turkish, Arabic, Hindi, Japanese, Korean, Thai, and Romanian.

Transparent Tiered Pricing

Frequently Asked Questions

Does TerpScribe send my audio to the cloud?

No. All audio capture and speech recognition happen locally on your Mac using an offline speech model. No audio is ever transmitted to or stored on any server.

Is TerpScribe a replacement for manual note-taking during consecutive interpretation?

No, TerpScribe is designed to augment your manual note-taking, not replace it. By automatically isolating and highlighting case numbers, dates, street addresses, proper names, and specialized terminology in a dedicated sidebar, it handles the exact details for you, freeing up cognitive capacity so you can focus on message structuring and delivery.

Is TerpScribe a replacement for an official court reporter or certified stenographer?

No. TerpScribe is a personal reference tool for the interpreter's own use during consecutive interpretation. It is not a certified or official record of any proceeding. See our Terms of Use for full detail.

Does TerpScribe work on Windows?

No, TerpScribe is currently macOS-only, and specifically requires an Apple Silicon Mac (M1 or later) — the offline speech model relies on Apple's on-device machine learning framework, which isn't available on Intel Macs or other platforms.

Is there a free trial?

Yes, new accounts include a 14-day free trial period before a subscription is required.

How do I get TerpScribe to transcribe audio from Zoom or Teams?

TerpScribe features a built-in setup wizard that automates most of the configuration for you. However, you will still need a free virtual audio driver called BlackHole to route the call's audio into the app. The setup wizard inside the app will guide you through installing and configuring it step-by-step, and we also have a detailed setup guide if you prefer manual configuration.

See all questions →