DC 5V / 2A Ai Smart Speaker Wi-Fi 2.4GHz / Bluetooth 5.0

SmartX Speaker Product Manual

1. Product Overview

The SmartX Speaker is an intelligent voice assistant that integrates AI voice interaction, visual recognition, multimodal understanding, IoT device management, and high-fidelity audio processing.
Powered by an advanced AI engine and the MCP (Multi-Component Platform) ecosystem, SmartX Speaker provides users with a seamless, natural, and powerful smart living experience through speech, vision, and automation.

2. Core AI Capabilities

AI Voice Interaction

• Supports real-time voice input and recognition.
• Enables intelligent human–machine interaction with natural and fluid conversational experiences.
• Provides semantic understanding and contextual dialogue for multi-turn interactions.

Visual Multimodal Processing

• Supports image recognition and visual understanding for multimodal interactions.
• Capable of interpreting image content, identifying objects, and answering visual-based queries.

Smart Wake-Up

• Supports multiple customizable wake words for hands-free activation.
• Users can configure wake-up functionality as needed to avoid manual operation.

Automatic Dialogue Mode

• Enables continuous dialogue without repeated wake-ups.
• Improves conversation fluency and maintains context across sessions.

3. MCP Tool Ecosystem

The MCP (Multi-Component Platform) provides a comprehensive suite of intelligent tools and utilities, offering versatile extensions and rich interactive experiences.

System Control Tool

• Includes system status monitoring, application management, volume control, and device management.

Schedule Management Tool

• Full-featured calendar system supporting creation, querying, updating, and deletion of events.
• Provides intelligent classification, reminders, and natural language scheduling.

Timer & Task Tool

• Built-in countdown and delayed execution functions.
• Supports parallel task management and multi-task coordination for MCP tools.

Music Player Tool

• Online music search and playback with real-time control.
• Supports play/pause, lyric display, and local cache management.

12306 Railway Query Tool

• Provides ticket inquiries, transfer searches, and train route lookups.
• Offers fast voice-based access to travel information.

Search Tool

• Supports Bing-powered web search and intelligent content parsing.
• Retrieves and summarizes webpage content with AI optimization.

Map Tool

• Integrated with Amap (Gaode) services for geocoding, path planning, and nearby searches.
• Supports real-time weather information and route navigation.

Camera Tool

• Captures images for AI-based analysis and recognition.
• Supports visual question answering and real-time camera intelligence.

4. IoT Device Integration

Device Management Architecture

• Unified Thing-based device management model.
• Supports asynchronous property access and method invocation for multiple devices.

Smart Home Control

• Enables control of lighting, volume, temperature sensors, and other smart devices.
• Supports voice-triggered automation and multi-device orchestration.

State Synchronization Mechanism

• Provides real-time state monitoring and incremental updates.
• Supports concurrent status retrieval and synchronized feedback.

Scalable Design

• Modular device driver framework allows easy integration of new device types.
• Compatible with mainstream IoT protocols (MQTT, HTTP, WebSocket).

5. Advanced Audio Processing

Multi-Level Audio Processing

• Supports Opus codec and real-time resampling for optimized performance.
• Delivers high-quality audio for both voice and music playback.

Voice Activity Detection (VAD)

• Intelligent VAD engine detects speech activity in real time.
• Enables smart interruption and adaptive microphone control.

Wake Word Detection

• Based on Sherpa-ONNX offline speech recognition engine.
• Supports multiple wake words and phonetic matching with low latency.

Audio Stream Management

• Independent input/output stream architecture.
• Supports stream reconstruction and automatic recovery after errors.

Acoustic Echo Cancellation (AEC)

• Integrated WebRTC audio processing module for premium echo and noise suppression.

System Audio Recording

• Supports system audio loopback recording for media analysis and playback management.

6. Technical Specifications

7. Package Contents