pulaoecho-voice-assistant

Name: pulaoecho-voice-assistant
Availability: InStock
Author: Arry8

Stream PCM audio from remote devices to a centralized gateway for wake-word, ASR, and TTS.

1|Updated Mar 30, 2026

Search Tags:#tts #websocket #asr #wake-word #voice-assistant #multidevice

Ready to run

npx skills add https://github.com/Arry8/openclaw-edge --skill pulaoecho-voice-assistant

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pulaoecho-voice-assistant
Source: https://github.com/Arry8/openclaw-edge/tree/main/skills/Pulaoecho-voice-assistant
Command: npx skills add https://github.com/Arry8/openclaw-edge --skill pulaoecho-voice-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, pydub, gtts, websocket-client, websockets, webrtcvad, numpy, cryptography, sherpa-onnx, and includes scripts (resource) components.

What problem does it solve?

Remote audio devices require a centralized, reliable voice assistant that can handle real-time audio streams, wake-word detection, speech recognition, and natural language response generation across multiple devices.

Core Features & Use Cases

Wake-word detection and per-device isolation for concurrent sessions
WebSocket-based streaming of PCM audio with TLS support
ASR with selectable engines (Aliyun or Sherpa-ONNX) and OpenClaw query integration
TTS generation and per-device playback with signaling (wake, process, feedback, sleep)

Quick Start

Run the service and connect a device via the WebSocket audio stream, then wake with your wake word to start interaction.

Frequently Asked Questions about pulaoecho-voice-assistant

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I stream PCM audio from multiple devices to a centralized voice assistant gateway?▼

The gateway streams PCM audio from multiple devices over TLS-encrypted WebSocket connections, providing per-device isolation for concurrent wake-word detection, ASR processing, and TTS response generation across all connected remote hardware.

Can I use Sherpa-ONNX instead of Aliyun for speech recognition in a multi-device setup?▼

Yes, you can use Sherpa-ONNX or Aliyun as selectable ASR engines for multi-device speech recognition. Both engines process incoming WebSocket audio streams and route asynchronous recognition results through OpenClaw integration for per-device response handling.

What is per-device isolation in a WebSocket-based voice assistant architecture?▼

Per-device isolation in a WebSocket-based voice assistant architecture ensures independent audio stream processing, wake-word detection, and signaling workflows for each connected device. It maintains separate concurrent sessions so recognition and TTS playback routing never cross between devices.

How does wake-word detection and signaling work for remote audio devices?▼

Wake-word detection triggers per-device signaling workflows consisting of wake, process, feedback, and sleep states. As PCM audio streams through the WebSocket gateway, the system isolates the active session, runs ASR, generates TTS, and routes playback back to the specific originating device.

Do I need TLS encryption for WebSocket audio streaming in a multi-device voice assistant?▼

TLS encryption is required for WebSocket audio streaming in this multi-device voice assistant to secure PCM audio transmission. It protects wake-word detection, ASR, and TTS signaling workflows between remote devices and the centralized gateway during concurrent sessions.

What are the limitations of using WebSocket streaming for real-time TTS and ASR across multiple devices?▼

WebSocket streaming for real-time TTS and ASR across multiple devices requires continuous PCM audio transmission and stable network connectivity. Latency depends on the selected ASR engine, and concurrent session scaling is bounded by gateway resources managing per-device isolation and signaling workflows.