> For the complete documentation index, see [llms.txt](https://guide.petoi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.petoi.com/product/quaddle-under-construction/control-and-program/ai-conversation.md).

# AI conversation

Quaddle's AI core board supports two AI conversation solutions: **TuyaOpen** and **Xiaozhi**. Both are open-source software architectures and share the following characteristics: the ESP32 can be used as a voice and sensing terminal; complex, large-scale model inference is usually performed in the cloud or on a self-built server; both also support MCP, enabling dialogue models to access real device capabilities. We will also open-source our implementation code to facilitate learning and improvement for everyone.

<table><thead><tr><th width="152.4000244140625">Solution</th><th>Core Advantages</th></tr></thead><tbody><tr><td><strong>TuyaOpen</strong></td><td>Comprehensive integration with smart home ecosystem AI hardware; complete capabilities including Tuya Cloud, device authentication, network configuration, OTA updates, App integration, and Google Home/Alexa; supports multiple platforms such as ESP32, Tuya T series, and Raspberry Pi; comprehensive multimodal capabilities including voice, camera/image/file interaction; device MCP allows smart agents to directly adjust volume, take photos, and switch modes.</td></tr><tr><td><strong>Xiaozhi</strong></td><td>More suitable for DIY, prototyping, learning ESP32 voice AI, and highly customizable projects; MIT open source; rich community and compatible boards; mature voice interaction loop for ESP32, including wake words, real-time dialogue, screen expressions, camera, and power management; users can choose or deploy a server and extend smart home, search, and computer control capabilities through MCP.</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://guide.petoi.com/product/quaddle-under-construction/control-and-program/ai-conversation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.