Open Voice AI is an innovative, open-source platform that allows users to interact with a Large Language Model (LLM) using voice commands. This project is designed to be fully free, leveraging browser-native APIs and free-tier LLMs to create a seamless voice-based AI assistant. Key features include:

• Free & Open Source: No need for paid APIs, credits, or subscriptions.

• Voice Input (Speech-to-Text): Utilizes the Web Speech API for capturing voice commands.

• AI Processing: Integrated with OpenRouter’s free-tier models for intelligent responses.

• Voice Output (Text-to-Speech): Uses native browser SpeechSynthesis for spoken replies.

• Cross-Platform Compatibility: Works on Chrome and Edge browsers across various operating systems.

• Minimal Backend: A simple Express.js proxy to handle LLM requests securely.

• Customizable: Easily swap LLMs or extend functionality.

This project is ideal for developers and hobbyists interested in building accessible AI tools without financial barriers. It demonstrates a complete voice-based LLM interaction loop, making AI development more democratised and accessible.