Skip to content
TakoAPI
Back to skills

percept-voice-cmd

by jarvis563

Coding Agents & IDEs
354Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Voice command detection and action execution for OpenClaw agents.

Description

What This Skill Does

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.

When to Use It

  • 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

Example Workflow

INPUT

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

AGENT
  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

OUTPUT

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

Requirements

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

Installation

clawhub install jarvis563/percept-voice-cmd

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links