Saltar al contenido
TakoAPI
Volver a skills

voice-wake-say

por xadenryan

Apple Apps & Services
5.9kDescargas según clawskills.sh
4Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

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

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

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

Instalación

clawhub install xadenryan/voice-wake-say

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces