AIUI is a platform designed for seamless, two-way verbal communication with AI models, targeting users who envision a future of voice-first interfaces. It enables natural, continuous conversations with AI, aiming to replace traditional point-and-click interactions.

How It Works

AIUI operates by capturing voice input, processing it through a selected AI model (currently GPT-4 and GPT-3.5, with open-source models planned), and delivering a synthesized speech response. This approach facilitates a conversational flow, allowing users to interact with AI as they would with another person.

Quick Start & Requirements

• Install/Run: Use Docker. Build the image (docker build -t aiui . or docker buildx build --platform linux/arm64 -t aiui . for ARM64) and run a container (docker run -d -e OPENAI_API_KEY=<YOUR_API_KEY> -e TTS_PROVIDER=EDGETTS -e EDGETTS_VOICE=en-US-EricNeural -p 8000:80 aiui).
• Prerequisites: An OpenAI API key is required. Text-to-speech (TTS) provider can be configured (defaults to EdgeTTS).
• Access: Navigate to localhost:8000 in a modern browser.
• Configuration: Environment variables OPENAI_API_KEY, AI_COMPLETION_MODEL (e.g., gpt-4), LANGUAGE, and TTS_PROVIDER can be set.

Highlighted Details

• Supports GPT-4 and GPT-3.5 models.
• Works in desktop and mobile browsers.
• Configurable TTS providers and voices.
• Language support is available, with specific TTS providers required for non-English languages.

Maintenance & Community

The project encourages starring the repository to gauge popularity and inform development efforts. No specific community channels or contributor information are detailed in the README.

Licensing & Compatibility

The repository's license is not specified in the README.

Limitations & Caveats

Support for open-source AI models is under development. Non-English language support is dependent on the chosen TTS provider.