This project provides a Python-based conversational AI chatbot that leverages OpenAI's Assistants API for engaging, emotive spoken or CLI interactions with ChatGPT and GPT-4. It's designed for users who want a more interactive and personalized AI experience, offering features like conversation memory, customizable voices, and adjustable creativity settings.

How It Works

The chatbot utilizes OpenAI's Assistants API to manage conversational context and state. It integrates speech-to-text (STT) for voice input and text-to-speech (TTS) for spoken output, with options for Google TTS, ElevenLabs TTS, or a robotic voice. Conversation history is managed to maintain context within token limits, and a memory system allows the bot to retain information across sessions, stored in a memories.txt file.

Quick Start & Requirements

• Install: pip install -r requirements.txt --upgrade (Windows) or pip3 install -r requirements.txt --upgrade (Linux, after sudo apt install python3-pyaudio espeak).
• Prerequisites: Python 3, OpenAI API key, potentially ElevenLabs API key.
• Setup: Requires placing API keys in keys.txt.
• Usage: python main.py <OpenAI key> [ElevenLabs TTS key] or python gptcli.py <OpenAI key>.
• Docs: Example Presets

Highlighted Details

• Supports spoken and CLI interactions.
• Offers conversation memory persistence across sessions.
• Integrates with ElevenLabs TTS for customizable, lifelike voices.
• Allows voice command control for various settings (model, creativity, TTS).
• Includes content moderation using OpenAI and NLTK.

Maintenance & Community

The project appears to be maintained by a single developer, Adri6336. There are no explicit mentions of community channels like Discord or Slack, or a public roadmap.

Licensing & Compatibility

The README does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project notes that it was "Made for old completion engine and retrofitted for ChatGPT. Not as good as modern stuff." It also warns that running directly from cloned repositories might be unstable. Latency or outages with OpenAI's moderation API can prevent usage unless the moderation check is manually removed from the code.