This project provides a Python-based voice assistant capable of interacting with both Bing AI via EdgeGPT and GPT-3.5-Turbo through its API. It targets users seeking a hands-free interface for these AI models, offering local speech-to-text and cloud-based text-to-speech.

How It Works

The assistant utilizes OpenAI Whisper for local speech transcription, ensuring privacy and potentially lower latency for voice input. For speech synthesis, it leverages AWS Polly, a cloud service known for its high-quality, natural-sounding voices. The core functionality involves recognizing two distinct wake words to route user queries to either the Bing AI (EdgeGPT) or the GPT-3.5-Turbo API.

Quick Start & Requirements

• Install: pip install -r requirements.txt
• Prerequisites: Python 3.7+, OpenAI API key, AWS credentials (for Polly), EdgeGPT setup.
• Resources: Local Whisper model download, AWS Polly usage may incur costs.
• Docs: YouTube Tutorial: https://youtu.be/aokn48vB0kc

Highlighted Details

• Dual AI model support (Bing AI via EdgeGPT, GPT-3.5-Turbo API).
• Local transcription using OpenAI Whisper.
• Text-to-speech powered by AWS Polly.

Maintenance & Community

No specific community channels or maintenance activity are detailed in the provided README.

Licensing & Compatibility

The license is not specified in the README. Compatibility for commercial use or closed-source linking is undetermined.

Limitations & Caveats

The project requires significant setup for API keys and potentially EdgeGPT. AWS Polly usage may incur costs. The README does not specify the license, which could impact commercial use.