AirTypes is a 100% offline voice-to-text app for Linux & macOS — speak naturally, release the hotkey, and your words appear at the cursor in any app. Filler words removed, grammar fixed, tone applied. No internet. No cloud. Nothing leaves your device.
Works inside any app on your system
Install it once. No account needed to start. No configuration. Just speak.
Press and hold Ctrl+Shift+Space from anywhere — VS Code, Slack, Gmail, a terminal. Works system-wide, no matter which app is in focus. Fully customizable.
Talk at your own pace. A floating overlay shows a live waveform so you know it's listening. Everything is processed locally on your CPU — no network request leaves your machine.
um like i wanted to talk about the deadline
I wanted to talk about the deadline.
Let go and your words appear at your cursor — cleaned, polished, ready. Filler words stripped, grammar fixed, tone applied. All locally, zero latency.
You speak at 150 WPM. You type at 50. That's 3× more output with less effort — and AirTypes automatically cleans up filler words and grammar for you.
Speed Comparison
Whether you write code, essays, emails, or AI prompts — if you spend time typing, AirTypes gives that time back.
"Review PR 142, the auth token refresh logic needs a retry with exponential backoff..."
Dictate code comments, PR descriptions, Slack messages, and documentation without leaving your editor. Works in VS Code, terminals, and every dev tool.
"The key difference between TCP and UDP is that TCP guarantees delivery order..."
Write essays, answer discussion posts, and take lecture notes by speaking. Your thoughts flow faster than your fingers — let them.
"The protagonist realizes the letter was never meant for her — it was a warning..."
Dictate first drafts, blog posts, and copy. Speak 3x faster than you type, and the built-in cleanup handles grammar and tone so your drafts are ready sooner.
"Prompt, build me a dashboard that shows weekly revenue grouped by plan type..."
Speak your AI prompts instead of typing them. The My Agent feature routes your voice through GPT-4, Claude, or any AI — and types the response at your cursor.
"Email, let the team know the sprint review is moved to Thursday at 3pm..."
Emails, Slack messages, meeting notes, reports. Speak them into any app and AirTypes applies the right tone — formal, professional, or casual.
"My wrists used to ache by noon. Now I speak 80% of what I write..."
If typing causes you pain, AirTypes lets you rest your hands while staying productive. Speak naturally — your words appear, cleaned up and ready.
A second hotkey routes your voice through any AI — GPT-4, Claude, Gemini, or a local model. Your words. Your key. Zero data through our servers. Ever.
Say the profile name first — the AI activates automatically
Works with any OpenAI-compatible provider — GPT-4o, Claude via OpenRouter, Gemini, Mistral, Groq, or a local Ollama model. One endpoint, one API key, done. We never see your credentials.
Create named profiles — Email, Prompt, Doctor, Developer, Casual. Say the name at the start of your speech and that profile's system prompt activates automatically. No menu, no clicking. Just speak.
Your API key is stored locally on your device only — never sent to AirTypes servers. When My Agent runs, your text travels directly from AirTypes to your chosen AI. We see nothing. We store nothing.
Hold a second hotkey and speak to your AI — ChatGPT, Claude, Gemini, or a local model. Say "Email, tell Sarah the deadline moved" and get a polished email typed at your cursor. Say "Prompt, build me a dashboard" and get a structured AI prompt ready to use. Your API key stays on your device.
See how it works →Your audio never leaves your device. Our on-device speech engine runs entirely on your CPU — no internet, no cloud, no subscription. Works in airplane mode, in sensitive environments, everywhere.
Not a browser extension. AirTypes injects text at your cursor system-wide — VS Code, Slack, Gmail, Terminal, Notion, Word, anywhere on your desktop.
The fastest model transcribes in under a second. Pick your speed-accuracy tradeoff — AirTypes optimizes CPU usage automatically.
Strips fillers (um, uh, like), fixes grammar, capitalizes sentences. Pick your tone: Formal, Professional, Neutral, Casual, or Friendly.
A subtle beep confirms recording start and stop — so you always know when AirTypes is listening. Toggle it on or off in Settings.
Native apps for Linux & macOS today; Windows on the roadmap — tiny footprint, blazing speed, native OS text injection on each desktop.
Every transcription saves automatically and persists across restarts. Browse up to 100 recent entries, paginated 20 at a time.
Ctrl+Shift+Space by default — change it to anything you like from Settings. Works system-wide across every app, no additional software required.
I write code comments, PR descriptions, and Slack messages all day. AirTypes saves me at least an hour. I just hold the hotkey, say what I mean, and it shows up exactly where I need it.
I use it for writing essays and answering discussion posts. Speaking my thoughts is way easier than staring at a blank page. The filler word cleanup is a lifesaver.
I switched from Wispr Flow because it sent my audio to the cloud. AirTypes does everything offline. The tone selector keeps my output consistent without editing.
The My Agent feature is incredible — I say "Email, tell the board we hit 10k users" and it drafts a polished email instantly. Typed right into my compose window.
I run Linux full-time and there's nothing else like this on the platform. Works in my terminal, and the hotkey is system-wide. Finally, voice typing that actually works on Linux.
Writing 5,000 words a day was destroying my wrists. Now I speak most of my first drafts. My RSI symptoms have genuinely improved. AirTypes cleans them up with the right tone.
I use the Prompt profile constantly. I say what I want and AirTypes shapes it into a proper AI prompt. Prompt engineering by voice — I didn't know I needed this until I tried it.
English is my second language and AirTypes still understands me perfectly. At $3.99/month it's cheaper than Grammarly and does more for how I actually work.
The privacy angle sold me. I work with sensitive client data. AirTypes processes everything locally — I verified it by running it with my network disabled. Still works perfectly.
I take notes during user interviews and AirTypes keeps up with natural conversation speed. It works in Notion, Google Docs, Figma — literally everywhere. Can't go back to typing notes.
Cloud voice apps send your audio to remote servers — they store it, analyze it, and own it. AirTypes processes everything locally on your hardware. Nothing leaves your machine.
You can request deletion — but it already touched a server. What happens next is up to them, not you.
We never hear your words. Your audio and transcriptions never leave your machine — ever.
These numbers are shown back to you in your dashboard — they are never sold, shared, or used to target you.
Your audio is processed entirely on your own device. It never touches a server.
Airplane mode, no WiFi, air-gapped machine — AirTypes runs without any internet connection.
Create a free account in seconds to download, sync settings, and add an optional profile photo. Your audio and transcripts still never leave your device.
Your usage stats stay in your account — never sold, never used for ads, never seen by us.
Choose the Whisper tier that fits your speed and accuracy needs — from near-instant to maximum quality. Transcription runs entirely offline.
Fastest transcription. Great for quick notes, commands, and low-power devices.
The best starting point. Great speed with solid accuracy for everyday use.
Noticeably higher accuracy, still fast enough for real-time dictation.
Strong handling of accents and complex speech. Ideal for professional writing.
Near-maximum quality at 3× the speed of Deep. The sweet spot for demanding use.
Highest possible accuracy. For when only the absolute best will do.
7-day free trial. No credit card. Free signup. Cancel anytime.
Full access. No limits. No card needed.
Free signup, instant access. Download and go.
After your 7-day trial. Cancel anytime.
Billed $3.99/mo after 7 days. Cancel any time.
Native downloads for Linux and for macOS (Apple Silicon & Intel). Windows is next on the roadmap — subscribers get it at launch at the same price.
Free 7-day trial · Free signup in seconds · English language support
Everything you need to know about AirTypes, offline speech recognition, and My Agent.
AirTypes is a 100% offline voice-to-text desktop app for Linux and macOS today, with Windows in development. You hold a global hotkey (default: Ctrl+Shift+Space), speak naturally, then release. AirTypes uses Whisper AI running entirely on your CPU to transcribe your speech and type the result directly at your cursor — in any app, with no internet required.
Yes — 100% offline. All speech recognition happens locally on your device. Your audio never leaves your machine. AirTypes works in airplane mode, on air-gapped computers, in hospitals, government offices, and any environment where internet access is restricted or privacy is essential.
AirTypes works with every desktop application — VS Code, Slack, Gmail, Google Docs, Microsoft Word, Notion, Discord, Terminal, ChatGPT in your browser, and any other app. It injects text at your cursor system-wide using native OS keyboard injection, so there are no app-specific limitations.
Yes. With My Agent and a Prompt profile (or your own instructions), AirTypes sends your transcribed speech to your AI using your API key (BYOK). The model returns polished, structured text you can use with ChatGPT, Claude, Gemini, or any OpenAI-compatible provider. Whisper transcribes offline on your device; the AI call goes straight from your machine to your provider — nothing through AirTypes servers.
AirTypes differs in three key ways:
At $3.99/month, it is also more affordable than most alternatives.
AirTypes uses OpenAI Whisper AI — among the most accurate offline speech recognition models available. Accuracy scales with model size: the base model is excellent for everyday use, while Large V3 Turbo and Large V3 deliver near-human-level transcription accuracy for professional and technical content.
Yes. AirTypes automatically strips filler words (um, uh, like, you know, so), fixes grammar, capitalizes sentences, and applies your chosen writing tone. Choose from Formal, Professional, Neutral, Casual, or Friendly — all processed locally with no internet.
AirTypes offers a 7-day free trial with full access to all features — no credit card and a quick free signup. After the trial, AirTypes Pro is $3.99/month (introductory launch price, locked in for you forever). You can cancel anytime.
AirTypes offers 6 voice quality tiers — from ultra-light to maximum accuracy:
Yes. AirTypes supports 100+ languages via Whisper AI's multilingual models. You can set your language explicitly or use auto-detect mode. Languages include Spanish, French, German, Portuguese, Hindi, Japanese, Chinese, Arabic, and many more — all processed offline.
My Agent is a second mode in AirTypes that routes your voice through an AI before it is typed at your cursor. Where normal transcription types what you say verbatim, My Agent sends your speech to an AI that shapes, rewrites, or acts on it — then types the AI's output directly in your active app.
The flow is: hold the agent hotkey → speak → Whisper transcribes locally → text is sent to your chosen AI API → AI response is typed at your cursor. Everything from Whisper transcription to cursor injection is handled by AirTypes. Your AI call goes directly from your device to your provider — AirTypes never sees the content.
Yes — AirTypes is currently the only polished, paid, actively-maintained offline voice dictation app for Linux. Superwhisper supports macOS and iOS only; Windows is listed as "in progress" on their roadmap with no Linux version planned. AirTypes uses the same Whisper AI models as Superwhisper, runs 100% offline on your CPU, and includes features Superwhisper lacks — like My Agent (BYOK AI routing). At $3.99/month it is also significantly cheaper than Superwhisper's $849 lifetime fee.
The fundamental difference is privacy. Wispr Flow processes your audio on their cloud servers — your voice leaves your device. AirTypes is 100% offline: your audio never leaves your machine. Other differences:
If privacy and offline operation matter, AirTypes is the stronger choice. See the full Wispr Flow alternative comparison.
Yes. AirTypes is live on Linux now. Supported distributions include:
It requires x86_64 architecture and 4 GB RAM minimum. No GPU required — Whisper runs on CPU. macOS is also available now (Apple Silicon and Intel). Windows is in development; subscribers get it at launch at the same price.
My Agent works with any OpenAI-compatible API endpoint. This includes:
You bring your own API key. AirTypes only stores it locally on your device — it is never sent to our servers.
No. AirTypes sees nothing. Your API key is stored locally on your device only — never uploaded to our servers. When My Agent runs, your text travels directly from AirTypes on your machine to your chosen AI provider. AirTypes acts as a local bridge — we never see the request, the response, or the content of your voice.
This is architecturally enforced: the HTTP call to your AI provider is made by the AirTypes desktop app directly from your device, not via any AirTypes proxy or backend.
Linux and macOS are available now. Windows is in active development. Early subscribers who sign up today will get the Windows app the moment it ships — at the same $3.99/month price, with no extra charge.
Have a question, issue, or idea? We're here Monday–Friday and typically reply within a few hours.
Questions about billing, features, or partnerships. We reply within a few hours on business days.
[email protected]Want to walk through AirTypes or discuss a team rollout? Send a meeting request and we'll confirm times that work.
Schedule a meetingLaunch bonus
Share your email and we’ll send you a checkout code for Pro. Same code works when you upgrade — no cloud audio, works in any desktop app.