A voice-controlled terminal for developers. Speak commands, execute them instantly.
Website: audiobash.app | Remote control: remote.audiobash.app
- Voice-to-terminal - Speak naturally and have your words transcribed directly into the terminal
- Context-aware agent mode - AI understands your environment: current directory, recent output, errors
- Custom instructions - Add personal instructions for transcription and agent modes
- Custom vocabulary - Map spoken words to correct spellings (e.g., "next js" → "Next.js")
- CLI notifications - Audio chime when CLI tools request input/approval
- Split view - View up to 4 terminals simultaneously with 5 layout modes (single, horizontal, vertical, 2x2 grid, 1+2)
- Resizable panes - Drag dividers to resize terminal panes in split view
- Focus indicator - Voice badge shows which terminal receives voice commands in split mode
- Tab rename - Double-click tab names to customize them
- Multi-tab support - Run up to 4 terminal sessions simultaneously
- Quick directory navigation - Jump to recent or favorite folders with one click
- Multiple AI providers - Gemini 2.0/2.5 Flash, OpenAI Whisper, Claude, or ElevenLabs
- Auto-copy - Selected text is automatically copied to clipboard
- Always-on-top mode - Pin the voice panel while you work
- System tray - Runs quietly in background, accessible via global shortcuts
- Extensive keyboard shortcuts - 16 customizable shortcuts for power users
- Preview pane - Embedded web preview for localhost dev servers, HTML, images, and markdown
- Screenshot capture - Take screenshots of the preview pane (saves to current working directory)
- Auto-refresh - File watcher automatically refreshes preview when source files change
Download the latest .exe installer from Releases.
Download the .dmg from Releases, or build locally:
git clone https://github.com/jamditis/audiobash.git
cd audiobash
npm install
npm run electron:build:mac:arm64 # Apple Silicon (M1/M2/M3/M4)
npm run electron:build:mac:x64 # Intel MacsNote: The macOS build is unsigned. On first launch, right-click the app and select "Open" to bypass Gatekeeper. See macOS build guide for details.
git clone https://github.com/jamditis/audiobash.git
cd audiobash
npm install
npm run electron:build- Launch AudioBash - The app starts with your default shell (PowerShell on Windows, zsh on macOS)
- Press Alt+S (or Option+S on Mac) - Opens the voice panel and starts recording
- Speak your command - e.g., "list all files in the current directory"
- Press Alt+S again - Transcription is sent to the terminal
| Shortcut | Action |
|---|---|
Alt+S |
Start/stop voice recording |
Alt+A |
Cancel recording (abort without sending) |
Alt+M |
Toggle raw/agent mode |
Alt+R |
Resend last transcription |
| Shortcut | Action |
|---|---|
Alt+H |
Show/hide window |
Alt+L |
Cycle through layouts |
| Shortcut | Action |
|---|---|
Alt+C |
Clear terminal |
Alt+→ |
Focus next pane |
Alt+← |
Focus previous pane |
Alt+B |
Bookmark current directory |
| Shortcut | Action |
|---|---|
Alt+1-4 |
Switch to tab 1-4 |
| Shortcut | Action |
|---|---|
Alt+P |
Toggle preview pane |
Alt+Shift+P |
Capture screenshot |
- Auto-send - Automatically execute transcribed commands (toggle in settings)
- Pin mode - Keep voice panel open while working
Open Settings (gear icon in title bar) to configure:
- API Keys - Add keys for Gemini, OpenAI, Anthropic, or ElevenLabs
- Transcription model - Choose between cloud or local transcription
- Default shell - PowerShell, CMD, or Bash
- Visual theme - Select from multiple color schemes
- Scanlines - Enable retro CRT effect
- Gemini (recommended): Google AI Studio
- OpenAI: OpenAI Platform
- Anthropic: Anthropic Console
- Electron - Desktop application framework
- React 19 - UI framework
- TypeScript - Type-safe JavaScript
- xterm.js - Terminal emulator
- node-pty - Pseudoterminal bindings
- Tailwind CSS - Styling
- Vite - Build tool
# Install dependencies
npm install
# Run in development mode
npm run electron:dev
# Build for production
npm run electron:buildMIT
Joe Amditis (@jamditis)