This project provides an open-source, unofficial ChatGPT client with enhanced features for customization and user experience. It targets users who want more control over their ChatGPT interactions, offering voice capabilities and advanced chat management.

How It Works

The application leverages the OpenAI API for ChatGPT interactions and integrates with ElevenLabs for realistic text-to-speech, providing a voice-enabled chat experience. It also incorporates OpenAI Whisper for speech recognition, enabling voice input. The frontend is built with TypeScript and React, focusing on fast response times and a user-friendly interface.

Quick Start & Requirements

• Install and run via Docker: docker run -v $(pwd)/data:/app/data -p 3000:3000 ghcr.io/cogentapps/chat-with-gpt:release
• Requires OpenAI API key and optionally an ElevenLabs API key for voice features.
• Access the app at http://localhost:3000.
• Official hosted version available at: https://www.chatwithgpt.ai

Highlighted Details

• Realistic voice output via ElevenLabs TTS.
• Speech recognition powered by OpenAI Whisper.
• Customizable system prompts and response temperature.
• Searchable chat history and shareable chat sessions.
• Full Markdown support, including code, tables, and math.

Maintenance & Community

The project welcomes community pull requests. Further community engagement channels are not explicitly mentioned in the README.

Licensing & Compatibility

Licensed under the MIT license, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

API key management requires careful handling, especially when storing keys on the server for self-hosted instances, as unauthorized access could lead to API usage by others.