Zonia AI Documentation

Comprehensive guide to integrating and using Zonia AI platform.

Getting Started

This section provides a quick guide to help you get your first project running and explains platform features. Zonia AI offers multi-backend support, voice recognition, custom training, and more. Follow the sections below to quickly deploy and use Zonia AI in your environment.

Multi-Backend Support
Integrate with OpenAI, Anthropic, Google, and local LLMs.
Voice Recognition
Advanced text-to-speech and speech-to-text capabilities.
Custom Training
Import/export data for custom model training.

Installation

Prerequisites

  • Node.js 16+ or Python 3.8+
  • Valid API key from your Zonia AI dashboard
  • HTTPS-enabled environment (for voice features)

Quick Start

git clone https://github.com/zonia-ai/zonia-assistant.git
cd zonia-assistant
npm install
npm run dev

The application will be available at http://localhost:5173

Configuration

Environment Variables

Create a .env file in your project root with the following variables:

OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_API_KEY=AIza...
OLLAMA_BASE_URL=http://localhost:11434
RASA_BASE_URL=http://localhost:5005

Platform Settings

Configure window options in the config/settings.json file:

{
  "theme": "default",
  "background": "gradient",
  "voice": true
}

API Reference

Authentication

Authorization: Bearer YOUR_API_KEY

Chat Endpoint

POST /api/chat
{
  "model": "gpt-4",
  "messages": [{"role": "user", "content": "Hello!"}]
}

Voice Endpoint

POST /api/voice
{
  "audio": "base64-encoded-audio"
}

Voice Features

Speech Recognition

Our platform supports real-time speech recognition using Web Speech API and can be configured to work with different languages.

Text to Speech

Convert AI responses to natural-sounding speech output in multiple voices and languages.

Voice Configuration

{
  "voice": true,
  "language": "en-US",
  "speechSynthesis": true
}

Training & Customization

Customize training data for your assistant, or import a tailored set of domain and context for more accurate responses.

Custom Training Data

[
  {"role": "user", "content": "What is Zonia?"},
  {"role": "assistant", "content": "Zonia is an AI assistant..."}
]

Fine-tuning

Fine-tuning models are possible via the admin panel or special endpoints for enterprise users.

Training Configuration

{
  "training": true,
  "examples": [ ... ]
}

Deployment

Production Setup

  • Configure proper .env and app settings
  • Run npm run build for production
  • Deploy static files to your web server

Docker Deployment

docker build -t zonia-assistant .
docker run -p 5173:5173 zonia-assistant

Troubleshooting

Common Issues

  • Check API keys for correctness and that the service is enabled and you have sufficient credits.
  • Check browser permissions and ensure your browser supports the Web Speech API.
  • Microphone issues: Make sure the site is loaded over HTTPS and you’ve granted microphone permissions.

Getting Help