Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Voice Dictation

TUICommander includes local voice-to-text using Whisper AI. All processing happens on your machine — no cloud services.

Setup

  1. Open Settings → Services → Voice Dictation
  2. Enable dictation
  3. Download a Whisper model (recommended: large-v3-turbo, ~1.6 GB)
  4. Wait for download to complete (progress shown in UI)
  5. Optionally configure language and hotkey

Usage

Push-to-talk workflow:

  1. Hold the dictation hotkey (default: F5) or the mic button in the status bar
  2. Speak your text
  3. Release the key/button
  4. Transcribed text is inserted into the focused input element (textarea, input, or contenteditable). If no text input has focus, the text falls back to the active terminal PTY. The focus target is captured at key-press time.

The hotkey works globally — even when TUICommander is not focused.

Models

ModelSizeQuality
tiny~75 MBLow (fast, inaccurate)
base~140 MBFair
small~460 MBGood
medium~1.5 GBVery good
large-v3-turbo~1.6 GBBest (recommended)

Models are downloaded to <config_dir>/models/ and cached between sessions.

Languages

Auto-detect (default), or set explicitly: English, Spanish, French, German, Italian, Portuguese, Dutch, Japanese, Chinese, Korean, Russian.

Text Corrections

Configure word replacements applied after transcription:

SpokenReplaced with
“new line”\n
“tab”\t
“period”.

Add custom corrections in Settings → Services → Dictation → Corrections.

Audio Device

Select which microphone to use from the dropdown in dictation settings. Lists all available input devices.

Platform Notes

  • macOS: GPU-accelerated transcription via Metal
  • Linux/Windows: CPU-only transcription
  • Microphone permission is requested on first use (not at app startup)

Status Indicators

IndicatorMeaning
Mic button (status bar)Click/hold to start recording
Recording animationAudio is being captured
Processing spinnerWhisper is transcribing
Model downloadingProgress bar with percentage

Hotkey Configuration

Change the push-to-talk hotkey in Settings → Services → Dictation. The hotkey is registered globally via Tauri’s global-shortcut plugin.

Default: F5

Auto-Send

Enable ‘Auto-send’ in Settings > Services > Dictation to automatically press Enter after the transcribed text is inserted into the terminal. Useful when dictating commands.