GPT-4 Voice Assistant

GPT-4 Voice Assistant is a project that integrates with the GPT-4 API model, Web Speech Recognition and text-to-speech services to convert voice queries into spoken audio. The application uses Node.js for the server and JavaScript for the client-side interactions.

Features

• Query GPT-4 model to get responses based on voice input.
• Convert the GPT response into speech using the StreamElements API.
• Support for different voice options.
• Display responses and play audio directly in the browser.

Installation

1. Clone the repository:

   git clone https://github.com/mikartisan/gpt4-voice-assistant.git
   cd gpt4-voice-assistant
   

2. Install dependencies:

   npm install
   

3. Start the server:

   node server.mjs