🎙️ Voice Agent

Transform your Linux desktop with voice control. Natural language commands, global hotkeys, and AI-powered transcription.

Get Started Watch Demo

✅ Fully Functional

✨ Features

🎤

Voice Transcription

Convert speech to text using Puter's cloud-based AI with high accuracy and multiple language support.

⌨️

Global Hotkeys

Trigger recording with Right-Ctrl + Right-Shift. Works system-wide, even when other applications are focused.

🤖

AI Command Execution

Speak naturally and let AI interpret your commands. Execute shell commands, control applications, and more.

🖥️

Beautiful UI

Floating widget with visual feedback. Drag to move, right-click for menu. Always stays on top.

🐧

Linux Native

Built for Linux with support for both X11 and Wayland display servers. Lightweight and efficient.

🔧

Easy Setup

One-command installation with automatic dependency detection and configuration.

🚀 Installation

One-command setup (recommended):

curl -fsSL https://raw.githubusercontent.com/jdgafx/voice-agent/main/setup.sh | bash

This will automatically:

Install system dependencies
Set up Node.js and/or Python implementations
Configure Puter.ai authentication
Create desktop shortcuts and auto-start
Sync code to GitHub

Manual installation:

# Clone the repository
git clone https://github.com/YOUR_USERNAME/voice-agent.git
cd voice-agent

# Install dependencies
npm install

# Set up Puter token
export PUTER_TOKEN=your_token_here

# Start the agent
npm start