KoEmo How to Use

From installation to voice input, step by step.

Install

①

Download Free Trial

②

Double-click the downloaded file to run

③

Follow the setup wizard (default settings are fine)

④

After installation, launch KoEmo

Requirements: Windows 10/11 + NVIDIA GPU (CUDA) required.

Launch

> When you launch KoEmo, an icon appears in the system tray at the bottom-right of your screen.

> The settings window opens automatically. If you can see the icon, you're ready to go.

Works right away with default settings. No changes needed.

Note: On first launch, KoEmo loads a ~2 GB speech recognition model into memory, which may take around 20 seconds.

Voice Input

🎤

Mic

🧠

STT Engine

📝

Text Output

①

Click and focus the app you want to type into (Notepad, browser, etc.)

②

Press the "Start" button in KoEmo

③

Speak into your microphone

④

When you stop speaking, text is automatically pasted

After pressing "Start", the button turns into a red "Stop" button

Speak and the overlay shows real-time results

Direct Input

> Step 03 explained the behavior with Direct Input ON (default). Turn it OFF to review results before confirming.

Direct Input ON (Default)

Auto-pastes when you stop speaking. No keyboard needed.

Speak → Auto Paste → Done

Direct Input OFF

Review the result before confirming. For accuracy.

Speak → Review → Confirm

Unchecking Direct Input reveals "Confirm Key" and "Confirm Wait" settings

Keyboard Controls (Direct Input OFF)

When OFF, use these keys to control recognition results.

Shift

ConfirmInstantly paste text during recognition

Esc

CancelCancel anytime

Recognizing: Shift to confirm / Esc to cancel

Confirm: Shift to paste / Esc to cancel

TIP: Press Esc anytime to cancel. Works in both ON and OFF modes.

Settings

> If recognition isn't working well or gets cut off, try adjusting these two settings.

VAD Threshold

Default: 0.60

Sensitivity of Voice Activity Detection.
KoEmo constantly listens to your mic and uses this value to determine if someone is speaking.

0.1 Sensitive
Reacts to quiet voices
May pick up noise 0.9 Less sensitive
Requires clear speech
Resistant to noise

Guide: Quiet room: 0.3–0.5 — Noisy environment: 0.6–0.8

Silence Duration

Default: 0.8s

The length of silence before speech is considered finished.
When silence lasts this long, KoEmo finalizes the recognition result.

0.3s Quick response
Splits on brief pauses 2.0s Relaxed
Allows thinking pauses

Guide: Gets cut off? Raise to 1.0–1.5s. Want faster input? Try around 0.5s

Tray Menu

> Even after closing the settings window, KoEmo keeps running in the background.

> Right-click the system tray icon to control KoEmo quickly.

Stopped — Click "Start Recognition" to begin

Running — Click "Stop Recognition" to stop

$ troubleshoot

› Select the correct microphone in "Audio Device" settings
› Lower the VAD threshold (mic sensitivity) to detect quieter voices
› Check that your microphone is enabled in Windows Sound Settings

› Increase the Silence Duration to prevent splitting during pauses
› Make sure you're not too far from the microphone

› Click and focus the target app before you start speaking
› KoEmo pastes into whichever app was focused when speech began

› Use confirmation mode (Direct Input OFF) to choose from candidates
› Speak in shorter sentences for better accuracy
› Using KoEmo in a quiet environment improves recognition

Haven't tried it yet?

14-day free trial. Just install and go.

Try Free