100% Local · No cloud, no data leaves your machine
WhisperKey

Voice to text,
instantly.

WhisperKey lives in your menu bar. Hold a key, speak, release. Your words appear wherever your cursor is. 13 AI models, all running on-device.

Download for Mac See how it works ↓

Free & open source · macOS · Windows · Linux · Apple Silicon & Intel

You said: "Schedule a meeting with the team tomorrow at 3 PM"
Typed into: Slack — #general
Time: 0.8s · Parakeet V3 · on-device
13
AI Models
50+
Languages
<1s
Latency
0
Data Sent

Why WhisperKey

Everything runs locally on your machine. No subscriptions, no cloud, no limits.

🔒

Completely Private

All speech recognition runs entirely on your machine — Apple Neural Engine, GPU, or CPU. No audio is ever sent to any server.

🧠

13 AI Models

Choose the right model for your needs: Whisper, Parakeet, Moonshine, SenseVoice, GigaAM. From 31 MB ultra-fast to 1.6 GB highest accuracy.

🍎

Apple Intelligence

On supported Macs, use Apple Intelligence to refine your transcriptions — fix grammar, improve clarity, or reformat text automatically.

🎯

Works Everywhere

Text appears wherever your cursor is — Slack, email, Notes, browser, IDE, terminal. Any text field in any app.

🤖

LLM Post-Processing

Connect OpenAI, Anthropic, or any compatible API to polish transcriptions with custom prompts — summarize, translate, reformat.

🌍

50+ Languages

Transcribe in English, Chinese, Japanese, Korean, Russian, European languages, and more. Auto-detect or select manually. Translate to English on the fly.

⌨️

Flexible Input

Push-to-talk or toggle mode. Customizable global hotkeys. CLI control via whisperkey --toggle-transcription. Unix signals on Linux/macOS.

📋

History & Recordings

Browse past transcriptions, replay audio, and copy previous results. Configurable retention from 3 days to indefinite.

🎙

Any Microphone

Built-in mic, AirPods, USB headset, external condenser — switch input devices from the menu bar. Clamshell mode support for laptops.

Choose Your Model

Download once, run forever. Switch models anytime from the settings panel.

Parakeet V3

~478 MB · NVIDIA

Fast and accurate. The recommended default for most users.

Recommended 25 Languages

Moonshine V2 Tiny

~31 MB · Useful Sensors

Ultra-lightweight. Ideal for quick notes and low-memory machines.

Fastest English

Whisper Large

~1100 MB · OpenAI

Highest accuracy across all languages. Best for critical transcriptions.

Most Accurate 50+ Languages

SenseVoice

~160 MB · FunAudioLLM

Optimized for Chinese, Japanese, Korean, and Cantonese.

CJK Fast

GigaAM V3

~225 MB · SberDevices

Specialized Russian speech recognition, fast and accurate.

Russian Fast

+ 8 More Models

Whisper Small/Medium/Turbo, Parakeet V2, Moonshine Base/Small/Medium, Breeze ASR

Full range from 58 MB to 1.6 GB. English-only to multilingual. Speed vs accuracy — your choice.

All Free All Local

How It Works

1

Install & Grant Permissions

Open the app. Allow Microphone and Accessibility access when prompted. WhisperKey appears in your menu bar and downloads your chosen model.

2

Click into Any Text Field

Position your cursor where you want the text — an email draft, a Slack message, a code comment, anywhere.

3

Hold Your Hotkey and Speak

The menu bar icon turns purple while recording. Release to stop. Or use toggle mode for hands-free dictation. Customizable hotkey in settings.

4

Text Appears Instantly

Your speech is transcribed on-device in under a second and pasted into the active text field. Optionally refined by Apple Intelligence or an LLM.

Under the Hood

Engines

6 Model Engines

Whisper, Parakeet, Moonshine, SenseVoice, GigaAM, Apple Intelligence

Runtime

Tauri + Rust

Native performance with minimal memory footprint. React UI.

Processing

100% On-Device

Neural Engine, GPU, or CPU. Zero network calls for transcription.

Platforms

macOS, Windows, Linux

Apple Silicon, Intel x64, X11, and Wayland support.

UI Languages

17 Languages

English, Chinese, Spanish, French, German, Japanese, Korean, Arabic, and more.

Updates

Auto-Update

Built-in updater checks for new versions automatically via GitHub releases.

About

WhisperKey is a free, open-source voice-to-text app by Evgeny Lisovskiy. Built as part of the Level Up App Factory — an AI-first product studio shipping useful tools powered by on-device intelligence.

Source code on GitHub. Questions or feedback? Reach out at info@levelupbasket.com