跳到正文
TakoAPI
返回技能列表

percept-voice-cmd

由 jarvis563 提供

Coding Agents & IDEs
354下载量由 clawskills.sh 提供
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

Voice command detection and action execution for OpenClaw agents.

描述

该技能的功能

Detects wake words in ambient audio and routes spoken commands to an OpenClaw agent for execution. Supports built-in actions like email, reminders, calendar queries, and notes, plus arbitrary forwarding for custom commands. Speaker authorization limits command execution to approved voices.

Two-tier intent parsing (regex first, LLM fallback) keeps simple commands fast while still handling complex natural language.

何时使用

  • Sending an email hands-free while cooking
  • Setting a reminder without touching a keyboard
  • Checking today's calendar by speaking aloud
  • Taking a quick note during a meeting
  • Texting a contact while driving

示例工作流

输入

User says: "Hey Jarvis, remind me in 30 minutes to call the dentist"

智能体
  1. 1

    Percept buffers incoming transcript and detects the wake word "Hey Jarvis"

  2. 2

    Buffer extends 5 seconds to capture the full command

  3. 3

    Intent parser matches the reminder pattern via regex

  4. 4

    Contact and time parameters are extracted from the utterance

  5. 5

    Command is dispatched to the OpenClaw CLI to schedule the reminder

输出

Reminder set for 30 minutes from now with the note "call the dentist"

前置要求

  • percept-listen skill installed and running
  • Percept dashboard accessible on port 8960 for wake word and speaker configuration

安装

clawhub install jarvis563/percept-voice-cmd

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