Speak freely.
Type nothing.Write faster.Stay private.Work offline.Think out loud.Skip the keyboard.

Private voice dictation that works in every app.

$ curl -fsSL https://get.omniscribe.dev/install.sh | sh
No telemetry Linux native Transparent
Any text field

Not locked to one editor. Dictate into any text field.

🌐 Browsers⌨️ Terminals📝 IDEs💬 Slack💬 Discord✉️ Email📄 Google Docs📓 Notion📓 Obsidian🔧 VS Code🔧 Vim

100% private

Everything runs on your machine. Voice never leaves your device. We couldn't listen even if we wanted to.

Works offline (Pro)

Pro tier needs zero internet. Free syncs only a word counter every 5 hours. No audio, no text, just a number.

Instant, local STT

No cloud round-trip. Speech-to-text runs on your GPU or CPU. Words appear as fast as you speak them.

Why OmniScribe
What's included

Everything in Free. Pro adds unlimited words and full offline mode.

3 polish modes

  • Voice - cleans grammar, removes filler words
  • Notes - structures into Markdown bullet points
  • Email - formats as professional email

All processing is local and instant.

BYO-LLM

Use your own OpenAI, Anthropic, or local LLM keys. You control which model processes your text.

Per-mode hotkeys

Set your own key combos for Voice, Notes, and Email modes. Switch instantly without opening the dashboard.

Fully configurable

Hotkey, microphone, VAD threshold, model size. One TOML file. Calibration wizard tunes for your voice.

Floating widget

Translucent pill lives above every window. Shows mode, word count, and recording status.

Terminal dashboard

Sign in, upgrade, switch modes, view usage. All from a terminal. No browser needed.

Wake word - soon Windows & macOS - soon

Free

$0/ forever

  • 500 words per 5-hour window (~2,400 / day)
  • All features: polish, BYO-LLM, hotkeys, widget, TUI
  • Requires internet connection
  • Sign up required
Download

Enterprise (team management, SSO, admin) and Windows & macOS coming soon.

Simple pricing
FAQ
Will it understand my accent?

OmniScribe uses Whisper models, the same speech recognition behind major transcription services. The calibration wizard tunes detection for your voice and microphone. Larger STT models available for higher accuracy. Calibration guide

Is my voice data safe?

Yes. Processing is 100% local. Your voice never leaves your device. Free tier syncs only a word counter (a number, not text). We are a subscription business. We don't collect, sell, or profile data. Privacy policy

Why sign up?

Sign up activates the app and enforces the free tier word cap fairly. Use Google, GitHub, Microsoft, or email. 30 seconds. No credit card for Free.

What does Free track?

Only your word count per 5-hour window. A single number. No audio, no transcripts, no keystrokes, no app usage. We can't see what you dictate.

Can I use my own LLM?

Yes. BYO-LLM on all tiers. Bring OpenAI, Anthropic, or local LLM keys. You control model, cost, and data. We never see your LLM requests.

Wayland support?

Yes. X11 and Wayland both supported via ydotool. Some Wayland compositors restrict global hotkeys. Try X11 if hotkeys don't register.

Business model?

We sell Pro subscriptions. $5/month for unlimited words and offline. No ads, no data sales, no VC. Our incentives align with yours.

Your voice belongs to you.

Private. Offline on Pro. Free to start.

Download