無程式碼也能輕鬆打造專業LINE官方帳號！一鍵導入模板，讓AI助你行銷加分！
Smart speakers are everywhere but their built-in voice assistants often lack the intelligence and flexibility of modern LLMs. XiaoGPT, created by yihong0618, bridges this gap by connecting XiaoAi smart speakers directly to ChatGPT, enabling natural, intelligent voice conversations through your existing smart speaker hardware.
The project works by intercepting the audio stream from a XiaoAi speaker, sending speech recognition results to ChatGPT, and playing the AI’s response back through the speaker. The result is a smart speaker upgrade that preserves all original functionality while adding powerful LLM capabilities.
Key Features
| Feature | Description |
|---|---|
| ChatGPT integration | Voice conversations through ChatGPT |
| XiaoAi speaker support | Works with XiaoAi smart speakers |
| Wake word detection | Activates on custom wake words |
| Continuous conversation | Maintains context across interactions |
| Original mode | Switch back to native XiaoAi assistant |
System Architecture
flowchart LR
A[User Voice] --> B[XiaoAi Speaker]
B --> C[Audio Capture Service]
C --> D[Speech Recognition<br/>ASR]
D --> E[LLM Request<br/>ChatGPT / Claude]
E --> F[Text Response]
F --> G[Text-to-Speech<br/>TTS]
G --> H[Audio Playback]
H --> B
I[Wake Word Detection] --> CThe architecture captures audio from the smart speaker, transcribes it with ASR, sends the text to an LLM for processing, converts the response back to speech, and plays it through the speaker. The wake word detection ensures the system activates only when addressed.
Supported Components
| Component | Options | Notes |
|---|---|---|
| Smart speaker | XiaoAi (various models) | Most popular in Chinese market |
| LLM backend | ChatGPT, Claude, others | Configurable API endpoint |
| ASR engine | Various | Built-in or cloud-based |
| TTS engine | Multiple voices | Configurable voice selection |
| Wake word | Customizable | Set any phrase as trigger |
Setup Options
| Method | Difficulty | Features | Maintenance |
|---|---|---|---|
| Docker deployment | Easy | Full stack, all features | Low |
| Manual installation | Medium | Configurable, modular | Medium |
| Raspberry Pi | Hard | Dedicated hardware, portable | Medium |
For more information, visit the XiaoGPT GitHub repository and the XiaoMi IoT developer documentation.
Frequently Asked Questions
Q: Do I need a XiaoAi speaker to use XiaoGPT? A: Currently optimized for XiaoAi speakers, though the architecture can be adapted to other smart speakers.
Q: Does XiaoGPT require cloud services? A: Yes, it uses cloud ASR, LLM, and TTS services for full functionality.
Q: Can I use local LLMs instead of ChatGPT? A: Yes, the system supports configurable API endpoints for local or cloud models.
Q: Will XiaoGPT break or disable my original speaker functions? A: No, original functionality is preserved and you can switch between modes.
Q: Is Chinese required to use XiaoGPT? A: No, it supports multiple languages through the LLM and ASR configurations.
