This repository provides configuration files for self-hosting the FoloToy Community Server, enabling users to run a personalized, AI-powered conversational experience. It targets users who want to integrate advanced LLM, Speech-to-Text, and Text-to-Speech capabilities into their own infrastructure.

How It Works

The server acts as a central hub, orchestrating interactions between various AI services and a MQTT broker for conversational data. It supports a range of popular LLM providers (OpenAI, Gemini, etc.), STT services (Whisper, Aliyun ASR), and TTS engines (Elevenlabs, EmotiVoice, OpenVoice AI), offering flexibility in choosing backend AI models.

Quick Start & Requirements

• Primary install / run command: git clone https://github.com/FoloToy/folotoy-server-self-hosting.git folotoy-server
• Prerequisites: Access to LLM, STT, and TTS API keys/services.
• Documentation: https://docs.folotoy.com

Highlighted Details

• Supports multiple LLM providers including OpenAI, Azure OpenAI, Google Gemini, Baidu Qianfan, Dify, and Moonshot.
• Integrates with various Speech-to-Text (STT) and Text-to-Speech (TTS) services like OpenAI Whisper, Elevenlabs, and Netease EmotiVoice.
• Conversational data is published to a MQTT Broker.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels are provided in the README.

Licensing & Compatibility

The repository does not explicitly state a license.

Limitations & Caveats

The project requires users to procure and configure API access for all integrated AI services. The absence of a specified license may pose compatibility concerns for commercial or closed-source applications.