Introducing JustVoice: The Fastest, Most Private Voice Transcription for Mac

We built JustVoice because we were tired of choosing between speed and privacy.

Every dictation tool we tried either shipped our voice to someone else's servers, produced sloppy output riddled with errors, or both. We wanted something that felt different — fast, intelligent, and fundamentally private. So we built it.

Today, we're launching JustVoice for macOS.

> Update (June 2026): Since this launch post, JustVoice has changed in two big ways. Pricing is now a single $35 one-time lifetime license — we retired the Free/Plus/Pro subscriptions entirely and grandfathered every existing subscriber to lifetime at no charge. And JustVoice is now 100% local: we removed cloud sync, so transcripts never leave your Mac. The sections below have been updated to reflect that; see the pricing page for current details.

What is JustVoice?

JustVoice is a voice-to-text app that turns your speech into clean, polished text — in any app on your Mac. Press a key, speak your mind, release. Your words appear wherever your cursor is, properly punctuated and formatted.

The key difference: everything happens on your device by default. Your audio is never sent to a server. There's no cloud dependency, no internet requirement, and no recording stored anywhere. Your voice stays yours.

The Problem We're Solving

You speak at roughly 150 words per minute. You type at maybe 40. That 4x gap is where ideas get lost — thoughts that fade while your fingers struggle to keep up.

Built-in macOS Dictation sends your audio to Apple's servers. Third-party tools like Otter or Rev are cloud-only by design. And the output from most speech-to-text engines still requires significant manual cleanup.

JustVoice closes every one of those gaps.

How It Works

When you hold your hotkey and speak, here's what happens under the hood:

1. Audio capture — Your microphone input is captured at 16 kHz with a high-pass filter to remove background noise.
2. Voice activity detection — A multi-layer VAD system (GMM-based with energy fallback) determines exactly when you're speaking and when you're not, filtering out clicks, breaths, and background noise.
3. Local transcription — OpenAI's Whisper model runs directly on your Mac's GPU via Metal acceleration. We support multiple model sizes from the lightweight Base (142 MB) up to the Turbo model (547 MB) for maximum accuracy across 90+ languages.
4. Intelligent cleanup — Your raw transcription passes through a rule engine that removes filler words ("um", "uh"), handles punctuation dictation ("comma", "period"), detects self-corrections ("actually, I mean..."), and formats lists.
5. Text insertion — The final text is inserted at your cursor position using adaptive timing calibrated for each app type — native macOS apps, Electron apps, and terminal emulators each get tuned delays for reliable insertion.

Features That Set JustVoice Apart

Works Everywhere on macOS

JustVoice isn't limited to a specific text field or app. Dictate into Mail, VS Code, Slack, Chrome, Notes, Pages, your terminal — anywhere you can type. A single configurable hotkey (Fn, Right Option, Right Command, or Ctrl+Shift) activates dictation system-wide.

App Profiles

Create custom App Profiles to configure the language, cleanup settings, and formatting for any specific app. JustVoice detects which app you're using — VS Code, Xcode, Terminal, Slack, Mail — and applies the appropriate profile automatically.

Code Mode

For developers, Code Mode is built specifically for dictating code. It recognizes programming terminology, formats identifiers correctly, and understands the difference between "function" the word and function the keyword. When JustVoice detects you're in a code editor, it automatically injects relevant developer jargon into the transcription context for better accuracy.

Personal Dictionary and Snippets

Add custom terms — names, brand names, technical jargon, medical terminology — to your Personal Dictionary. Each entry can include a "spoken form" so JustVoice knows that when you say "A P I" you mean "API."

Snippets let you create voice-activated text shortcuts. Say a trigger phrase and JustVoice expands it into full text, complete with template variables like {date}, {time}, and {clipboard}.

File Transcription

Drop an audio file (WAV, MP3, M4A, OGG, FLAC, AAC, or WebM) into JustVoice and get a full transcription. The same Whisper engine that handles live dictation processes your files locally.

Notes

Every transcription is saved locally in a built-in Notes system backed by SQLite. View your raw transcription or the cleaned version, revert if needed, and search through your history. Notes stay entirely on your Mac — there's no cloud sync.

Sound Effects and Visual Feedback

Optional audio cues play when dictation starts and stops, so you always know when JustVoice is listening. A floating overlay provides real-time visual feedback as your words are transcribed.

Simple Pricing: $35 Once, Yours for Life

We no longer have tiers. JustVoice is a single $35 one-time payment for a lifetime license — no subscription, no monthly word caps, and nothing held back behind a higher plan.

• Unlimited dictation, forever — no monthly word cap
• All Whisper models — from Base (142 MB) up to the largest, most accurate models
• Code Mode — syntax-aware dictation with IDE detection for developers
• App Profiles — per-app tone, language, and cleanup settings
• Unlimited dictionary entries, snippets, and note history
• 100% local — transcripts never leave your Mac, and it works fully offline after activation
• Every future update included

Built for Apple Silicon

JustVoice is a native macOS application built with Tauri and Rust. The Whisper models run via Metal GPU acceleration on Apple Silicon, which means transcription is fast — significantly faster than real-time on M1 and newer chips. Intel Macs are supported with reduced performance.

• macOS 13.0 (Ventura) or later
• Apple Silicon recommended (M1, M2, M3, M4)
• 4 GB RAM minimum, 8 GB recommended

Privacy Is the Default

We want to be direct about what JustVoice does and doesn't do with your data:

• Always local: Zero transcription data leaves your device. No audio is transmitted. No text is uploaded. No analytics are collected in the desktop app. Models run on your GPU. Notes are stored in a local SQLite database. Your config lives in a local JSON file. There is no cloud sync — we removed it.
• Authentication: Handled by Supabase. We store your email and license status. That's it.
• Payments: Processed entirely by Stripe. We never see your card number.

What's Next

This is version 1.0, and we have a clear roadmap ahead:

• More Whisper model options and fine-tuned models for specialized vocabularies
• Multi-language simultaneous dictation
• iOS and iPad companion app

Get Started

JustVoice is available today for macOS.

If voice is the most natural way to communicate, it should be the most natural way to write. That's what we built.

Welcome to JustVoice.