This project provides a ChatGPT-powered voice chat application with Live2D integration, targeting users who want an interactive, AI-driven companion experience. It leverages Text-to-Speech (TTS) and Voice Conversion (VC) technologies to enable natural voice conversations with customizable characters.

How It Works

The application integrates ChatGPT for conversational AI, a TTS engine (likely VITS based on dependencies) for speech generation, and a voice recognition system for user input. It supports multiple character voices and connects to a web-based Live2D viewer for visual representation, creating an immersive, interactive experience.

Quick Start & Requirements

• Install: Download and run ChatWaifuL2D.exe.
• Prerequisites: Latest Chrome browser (v108+), VPN (if in China), OpenAI API token.
• Setup: Install to a non-C: drive directory. Run ChatWaifuServer.exe and then ChatWaifu.exe.
• Docs: BiliBili Demo

Highlighted Details

• ChatGPT conversational chat.
• Text-to-speech with multi-character voice support.
• Voice recognition for interactive dialogue.
• Live2D web integration.
• Marai robot integration.

Maintenance & Community

The project acknowledges dependencies on MoeGoe_GUI, TTSModels, and PyChatGPT. No specific community links or active maintenance signals are present in the README.

Licensing & Compatibility

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

Limitations & Caveats

The project requires specific browser versions and may necessitate a VPN for users in certain regions. Obtaining an OpenAI API token involves accessing browser developer tools, which might be a barrier for less technical users. CUDA acceleration is mentioned for the official API version but only as source code.