voice-wake-say
par xadenryan
Apple Apps & ServicesRésumé
Speak responses aloud on macOS using the built-in `say`.
Description
Ce que fait ce 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.
Quand l'utiliser
- 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
Exemple de workflow
User asks: "User talked via voice recognition on MacBook: summarize my last three tasks"
- 1
Detect that the message starts with the Voice Wake trigger phrase
- 2
Run
sayimmediately to acknowledge the request aloud - 3
Perform the requested task
- 4
Strip markdown from the response text
- 5
Run
sayagain to speak the summary
macOS speaks the acknowledgment and summary aloud; full text response also appears on screen
Installation
clawhub install xadenryan/voice-wake-sayExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.