YOUR VOICE. YOUR CHOICE.

Free, open-source
local voice input.

Turn speech into text, on your own computer.
No subscription. Dictate offline after downloading a model. Connect your preferred AI only when you want refinement or translation.

Windows · macOS · Linux

VOICE → TEXTON DEVICE
Today’s ideas.md
Text Aa  B  /  ≡

A LITTLE ROOM TO THINK

Start with a thought.

Say what’s on your mind.
Give your ideas a place to land.

What will you write next?

A thought, now in wordsRecognized on this device

Illustrative preview · Stay in the app you’re using

ON-DEVICE RECOGNITION

Your voice stays on your device.

Speech recognition runs on your computer. Download a model and leave cloud refinement and translation off to dictate offline.

MIT LICENSED

A useful tool. Not another subscription.

Core dictation is free. The code is available under the MIT license to inspect, modify, and build yourself.

OPTIONAL AI REFINEMENT

Your words. Your choice of AI.

Keep the transcription as it is, or connect your preferred provider for refinement and translation. Provider charges may apply.

MADE FOR YOUR EVERYDAY

Stay in your flow.
Let your voice do the typing.

Reply to a message, work through an idea, or describe what to build. Put your words in the app you’re already using.

Project chat

Let’s talk about the new design tomorrow morning. I’ll send my notes ahead of time.

Text inserted into the current appEXAMPLE

KNOW WHERE YOUR DATA GOES

Local at the core.
Optional beyond that.

Your audio is recognized on your computer. Sending text to a cloud AI is a separate choice that you make.

Explore privacy & data
YOUR COMPUTER
Audio→Text

No audio upload for recognition · Local history

↓ ONLY IF YOU ENABLE IT
Your chosen AI provider

Receives text for refinement or translation

Optional

THE DETAILS THAT HELP

Ready for everyday words.

01

Chinese and English, together

See live Chinese and English partial text in Streaming mode. Classic mode also supports Cantonese, Japanese, and Korean.

02

A dictionary of your own

Add names, abbreviations, and specialist terms for streaming hotword bias and optional AI-assisted corrections.

03

Find your words again

Search, copy, and manage your dictation history locally. Records remain until you choose to delete them.

GOOD TO KNOW

A few good questions.

Read the getting-started guide
Is Voice Key really free?

Voice Key is free and MIT licensed. Local recognition needs no ASR API key. Optional AI refinement and translation use your configured provider and may incur third-party charges.

Can I dictate offline?

Yes. Download a local model first and disable cloud refinement and translation. Core recognition and text insertion then work offline. Model downloads and update checks need a connection.

Which languages are supported?

Classic mode supports Mandarin, English, Cantonese, Japanese, and Korean. Streaming mode supports Chinese and English with live partial text in the HUD. The interface is available in English and Chinese.

Where do my audio and text go?

Local recognition does not upload microphone audio. If cloud refinement or translation is enabled, the relevant text and dictionary terms are sent to your configured provider. History stays on your device until you delete it.

What should I know before installing?

macOS requires Microphone and Accessibility permissions. Current builds are unsigned and may trigger system warnings. Linux supports X11 and a dedicated Omarchy / Hyprland integration; other Wayland environments are not fully supported. See the getting-started guide.

MAKE ROOM FOR YOUR IDEAS

Your next thought starts here.

Download Voice Key for free. Choose your desktop platform.

Download a recognition model on first use. Current builds are unsigned; read the installation & permissions guide.