본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

percept-voice-cmd

jarvis563 제작

Coding Agents & IDEs
354clawskills.sh가 보고한 다운로드 수
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Voice command detection and action execution for OpenClaw agents.

설명

이 스킬이 하는 일

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.

사용 시점

  • 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

예시 워크플로

입력

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

에이전트
  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

출력

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

요구 사항

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

설치

clawhub install jarvis563/percept-voice-cmd

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크