JARVIS is a personal voice assistant that converts spoken language to text, processes it with a Large Language Model (LLM), and then converts the response back to speech, all presented through a web interface. It is designed for users who want a customizable, AI-powered voice assistant integrated into a web application.

How It Works

The system utilizes a pipeline: user speech is captured via microphone and transcribed to text using Deepgram. This text is then sent to OpenAI's GPT-3 API for response generation. The LLM's text response is converted to speech using ElevenLabs and played back using Pygame. The entire conversation flow is displayed in a web interface built with Taipy.

Quick Start & Requirements

• Install: pip install -r requirements.txt
• Run: python display.py (web interface), python main.py (voice assistant)
• Prerequisites: Python 3.8-3.11, API keys for Deepgram, OpenAI, and ElevenLabs.
• Setup: Requires creating a .env file with API keys.

Highlighted Details

• Integrates Deepgram for Voice-to-Text, OpenAI (GPT-3) for LLM, and ElevenLabs for Text-to-Speech.
• Features a web interface powered by Taipy for displaying the conversation.
• Provides a clear, step-by-step conversational flow from listening to speaking.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels is provided in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not mentioned.

Limitations & Caveats

The project relies heavily on third-party API keys (Deepgram, OpenAI, ElevenLabs), which may incur costs. The README does not detail error handling or fallback mechanisms for API failures.