pulaoecho-voice-assistant
Integrate a voice-activated remote assistant into your projects with TTS and WebSocket support.
Install
mkdir -p .claude/skills/pulaoecho-voice-assistant && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11158" && unzip -o skill.zip -d .claude/skills/pulaoecho-voice-assistant && rm skill.zipInstalls to .claude/skills/pulaoecho-voice-assistant
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
远程音频语音助手，支持语音唤醒和TTS响应Key capabilities
- →Detect wake-words
- →Perform natural language processing
- →Stream audio responses via WebSocket
- →Support TLS encrypted connections
How it works
The service uses Python to manage a WebSocket server that processes audio streams. It detects wake-words, performs NLP, and returns TTS responses to the connected device.
Inputs & outputs
When to use pulaoecho-voice-assistant
- →Set up voice commands for hardware
- →Integrate voice assistant into an app
- →Stream audio responses over TLS
About this skill
Pulaoecho Voice Assistant
远程音频语音助手，支持语音唤醒和TTS响应。
功能
- 语音唤醒（支持 "hi claw", "hey claw", "hi google", "hey google", "ok google"）
- 语音识别和自然语言处理
- 文本转语音（TTS）响应
- WebSocket音频流传输
- TLS加密连接
配置
-
生成证书：
cd skills/Pulaoecho-voice-assistant && bash scripts/gen_cert.sh -
安装依赖：
cd skills/Pulaoecho-voice-assistant && pip3 install -r requirements.txt -
启动服务：
cd skills/Pulaoecho-voice-assistant && python3 scripts/main.py
使用
设备可以通过WebSocket连接到服务：
- WebSocket URL:
wss://localhost:18181/v1/audio/stream - 连接时需要发送包含deviceid的初始化消息
- 后续所有消息都需要包含deviceid字段
技术说明
- 服务使用Python实现
- WebSocket服务器处理音频流
- 语音助手核心逻辑处理唤醒词检测和自然语言处理
- 支持单声道和双声道音频数据
注意事项
- 服务默认使用自签名证书，客户端需要信任该证书
- 服务运行在18181端口
- 日志文件保存在当前目录的
pulaoecho-voice-assistant.log
When not to use it
- →When the environment does not support TLS or WebSocket connections
Prerequisites
Limitations
- →Requires client trust for self-signed certificates
- →Runs on a fixed port 18181
How it compares
It provides a dedicated voice assistant platform with integrated wake-word detection and streaming audio capabilities over TLS, rather than using generic voice APIs.
Compared to similar skills
pulaoecho-voice-assistant side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| pulaoecho-voice-assistant (this skill) | 0 | 5mo | Review | Intermediate |
| video-downloader | 101 | 7mo | Review | Beginner |
| 64 | 6mo | Review | Beginner | |
| openai-whisper | 38 | 2mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
video-downloader
ComposioHQ
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
anthropics
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
openai-whisper
openclaw
Local speech-to-text with the Whisper CLI (no API key).
video-processor
basher83
Process video files with audio extraction, format conversion (mp4, webm), and Whisper
google-calendar-sync
astoreyai
Manages Google Calendar through the Calendar API. Create, read, update, and delete events, manage multiple calendars, set reminders, handle recurring events, and sync with local schedules. Use when working with Google Calendar, scheduling events, checking availability, managing meetings, or automating calendar workflows.
setup
barefootford
Sets up a Mac for ButterCut. Installs all required dependencies (Homebrew, Ruby, Python, FFmpeg, WhisperX). Use when user says "install buttercut", "set up my mac", "get started", "first time setup", "install dependencies" or "check my installation".