Voice interface for terminal AI coding agents
Works with Claude Code, Aider, Cursor CLI, GitHub Copilot CLI, and any agent that runs in a terminal.
Launch App opens the web UI — requires the desktop app running in the background.
Speak naturally -- local Whisper STT transcribes on-device with zero cloud latency. Auto-listen detects speech and starts recording hands-free.
Responses read aloud via local Kokoro TTS. 60+ voices, adjustable speed (0.5x--3x), paragraph-level highlighting as your agent speaks.
Watch your AI agent working in real-time. Full ANSI color, scrollback, arrow key navigation, and interactive prompt detection.
Talk (full voice), Type (type in, hear back), Read (speak in, read response), and Text (keyboard only). Switch with one tap.
macOS and Windows via Electron. Floats above all windows, draggable header, visible on all workspaces. Auto-updates from GitHub.
Content updates (UI, server logic) pulled from GitHub on every launch. Shell updates via GitHub Releases. Always current, zero effort.
A focused, distraction-free conversation view. One tap hides all chrome — just the mic, flowing prose in a serif font, and nothing else. Barge-in and auto-listen keep the exchange natural.
Download, open, talk. That's it.
Download the app for macOS or Windows. Open it -- Murmur checks for prerequisites, starts your AI agent session, and connects automatically. A guided tour walks you through all controls on first launch.
Tap the talk button or press Right Cmd to start recording. Speak your request, release to send. The response appears as conversation bubbles and is read aloud. Or just type in the text input.
Tap the mode button to cycle between Talk, Type, Read, and Text. Each mode adjusts mic and speaker behavior. Expand the terminal panel to see the agent's full output and navigate with arrow keys.
Switch modes with a single tap on the mode button.
Use Murmur from your iPhone or any browser on your local network via Tailscale.
tailscale status to get your hostname (e.g. device.tailnet.ts.net)https://<hostname>:3458When both the desktop app and your phone are connected, the 🔊 dot in the top-right shows which device has audio output. The last-connected device automatically claims audio. Tap the 🔊 dot on any device to claim audio for it.
Use Kokoro voices (Heart, Sky, Adam, etc.) for audio on remote devices — device voices like Samantha only play on the Mac.
Grab the latest release for your platform.
No app download needed. Paste this in any terminal — then open localhost:3457 in your browser.
git clone https://github.com/hdt325/murmur.git && cd murmur && npm install && npm start
The desktop app adds a floating window, dock icon, and global hotkey — but the server works standalone in any browser.
git clone https://github.com/hdt325/murmur.git
cd murmur && npm install
cd electron && npm install && cd ..
npm run electron
npm i -g @anthropic-ai/claude-code), Aider (pip install aider-chat), or any CLI tool that runs in a terminal
uv tool install voicemode