Coming Soon - In Active Development

Your Voice.
Your PC.
Your Privacy.

100% offline voice-to-text for Windows. Hold a hotkey, speak, and text appears at your cursor. Open source, private by design, and completely free.

🔒 100% Offline
🛡️ Privacy First
📖 Open Source
🚫 No Data Leaves Your System
🆓 Free Forever
🖥️ Windows Native
📡 Zero Telemetry
Scroll

Everything runs on your machine.

No cloud. No accounts. No subscriptions. Just you, your voice, and your Windows PC.

🔒

Zero Network Calls

Audio is processed 100% on-device. Nothing is ever transmitted to any server. Your voice data stays on your PC. Always.

🗑️

No Audio Storage

Audio buffers are discarded immediately after transcription. Nothing is saved to disk. Ever. Your conversations stay yours.

📖

Fully Open Source

Every line of code is public on GitHub. Audit it yourself. No hidden anything. Transparent by default.

📡

No Telemetry

No analytics. No crash reporting. No usage tracking. We literally cannot see what you do. Your privacy is absolute.

⌨️

System-Wide Text Injection

Transcribed text appears wherever your cursor is. Browsers, Slack, VS Code, Word, Excel, terminals. Everywhere.

🎯

Push-to-Talk & Toggle

Hold a hotkey to record or double-tap to toggle. Simple, predictable, works exactly the way you expect.

🌍

99+ Languages

Auto-detect or specify your language. English, Spanish, French, German, Chinese, Japanese, and many more supported.

GPU Accelerated

Leverages NVIDIA CUDA, AMD, and Intel GPU acceleration for blazing fast transcription on Windows hardware.

⚙️

Fully Configurable

Choose hotkeys, models, languages, silence detection thresholds. A settings panel that puts you in full control.

Three steps. That's it.

No accounts. No sign-ups. No cloud. Just install and speak.

1

Press Your Hotkey

Press and hold your chosen hotkey. The system tray icon lights up. You're recording.

2

Speak

Say whatever you want. Your audio is processed entirely on your PC. Nothing leaves your machine.

3

Release

Text appears at your cursor. In any app. Browser, Slack, VS Code, Word. Anywhere on Windows.

Voice-to-text on every platform.

VocaWin joins a family of privacy-first, offline voice dictation tools. Same mission, every operating system.

Apple macOS

VocaMac Beta

100% offline voice-to-text for macOS. Apple Silicon native with CoreML & Neural Engine acceleration via WhisperKit.

Apple Silicon CoreML WhisperKit AGPL-3.0

Linux Linux

VocaLinux Beta

100% offline voice dictation for Linux. Powered by whisper.cpp with Vulkan GPU support. Works on X11 & Wayland across all major distros. The original.

whisper.cpp Vulkan GPU X11 & Wayland GPL-3.0

Be the first to know when VocaWin launches.

We're building voice-to-text for Windows the right way: private, offline, and open source. Star us on GitHub to follow progress.