跳到正文
TakoAPI
返回技能列表

voice-wake-say

由 xadenryan 提供

Apple Apps & Services
5.9k下载量由 clawskills.sh 提供
4星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Speak responses aloud on macOS using the built-in `say`.

描述

该技能的功能

Reads assistant responses aloud on macOS using the built-in `say` command. Activates only when the user message starts with the exact phrase "User talked via voice recognition". Strips markdown before speaking and falls back to text if `say` is unavailable.

Uses the local macOS `say` command instead of cloud TTS, so responses work offline with no API keys or external accounts.

何时使用

  • Listening to assistant replies hands-free while working at a desk
  • Getting verbal acknowledgment when kicking off long terminal commands by voice
  • Dictating questions and hearing answers without looking at the screen
  • Using voice input on macOS without sending audio to cloud services
  • Confirming task completion during voice recognition sessions

示例工作流

输入

User asks: "User talked via voice recognition on MacBook: summarize my last three tasks"

智能体
  1. 1

    Detect that the message starts with the Voice Wake trigger phrase

  2. 2

    Run say immediately to acknowledge the request aloud

  3. 3

    Perform the requested task

  4. 4

    Strip markdown from the response text

  5. 5

    Run say again to speak the summary

输出

macOS speaks the acknowledgment and summary aloud; full text response also appears on screen

安装

clawhub install xadenryan/voice-wake-say

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接