🎙️ Voice Assistant: Mambo Acoustic Engine & Command Reference

ZZ Music integrates an on-device offline voice assistant. Voice control works with no internet connection.

⚡ 1. 'Mambo Era' Bilingual Wake Word Engine

• Dedicated Wake Word: "Mambo" (or Chinese "曼波")
• Compact Model: a 33KB ultra-lightweight ONNX acoustic model that runs in the background with a very low memory and CPU footprint.
• Multi-Frame Decision & Anti-Jitter:
  • Single-frame confidence ≥ 0.75 triggers immediate wake-up;
  • Average sliding window (400ms) ≥ 0.35 with peak ≥ 0.50 confirms wake-up;
  • 1.5-second cooldown suppresses accidental re-triggers from vocal echoes.

📖 2. Complete Local Commands Dictionary

Matches execute locally on-device, with no network round-trip:

Note: "zero delay" refers to command dispatch. Waking the assistant itself still requires roughly 240ms or more of continuous speech (see the 400ms sliding window and multi-frame confirmation above), and in online mode also depends on your chosen provider.

1. Playback & Track Skipping

• Next Track: "next", "skip", "play next", "下一首", "切歌"
• Previous Track: "previous", "go back", "上一首", "倒回去"
• Pause / Stop: "pause", "stop", "暂停", "别放了"
• Resume / Play: "play", "resume", "播放", "继续播放"

2. Playback Modes

• Shuffle Mode: "shuffle", "random", "随机播放"
• Single Repeat: "repeat one", "loop single", "单曲循环"
• List Repeat: "repeat all", "loop all", "列表循环"

3. Volume Control

• Volume Up: "volume up", "louder", "声音大点", "音量加"
• Volume Down: "volume down", "quieter", "声音小点", "音量减"
• Mute / Unmute: "mute", "静音" / "unmute", "取消静音"

4. Genre & Favorites

• Genre Requests: "play rock", "play jazz", "play pop", "放点流行", "听摇滚"
• Favorites: "like", "favorite", "add favorite", "收藏"
• Time & Query: "what time is it", "what song is this", "这是什么歌", "报时"

🎚️ 3. Hardware Audio Enhancement & AEC Tuning

Go to Settings -> "Voice Assistant & Wake Word" to tune the acoustic pipeline for your environment:

• Hardware Acoustic Echo Cancellation (AEC):
  • Enable Call-Source AEC: while the speaker is playing loud music, the hardware removes the song's echo from the microphone, greatly improving wake-word success rates while music is playing.
• Hardware Noise Suppressor (NoiseSuppressor) & Automatic Gain Control (AGC):
  • Automatically filters out fan airflow and car engine noise, improving far-field pickup clarity.
• Silence-Cutoff Sensitivity:
  • Supports three levels — High / Medium / Low. In quiet environments, raise the sensitivity so commands execute the moment you stop speaking.

🤖 4. Optional LLM Semantic Intent Parsing

For complex requests (e.g., "Play a soothing acoustic track for a rainy evening"), configure your API Key in Settings -> AI Settings (supports Qwen, DeepSeek, and Gemini).