mcp-tts vs py-xiaozhi
mcp-tts: `mcp-tts` is an MCP server that integrates various Text-to-Speech providers, including local macOS `say` and cloud APIs like ElevenLabs, Google TTS, and OpenAI TTS, into AI agent environments. It enables AI agents within tools like Claude Desktop and Cursor IDE to verbalize plans, summaries, and alerts, enhancing interactive communication.; py-xiaozhi: py-xiaozhi is a Python-based client for the Xiaozhi AI voice assistant, designed for learning through code and experiencing AI voice features without dedicated hardware. It integrates core AI capabilities like voice interaction, visual multi-modality, and smart wake-up, alongside a rich MCP tool ecosystem and IoT device integration.
TL;DR
Add Text-to-Speech capabilities to AI agent development environments (e.g., Claude Desktop, Cursor IDE) for interactive feedback.
- You want to try the Xiaozhi voice assistant on a computer without ESP32 hardware.
- You want offline wake words with Sherpa-ONNX, echo cancellation and a GUI or command-line mode.
- You want ready MCP tools such as schedules, timers, music, train tickets, web search and maps.
- You want a self-contained assistant: AI features depend on the Xiaozhi service.
- You cannot use Python 3.9 to 3.12, working audio devices and an internet connection.
- You want to self-host the backend: that is the server projects' job.
Side-by-Side Comparison
Features
Use Cases
FAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.