Setup & Installation
openclaw skills install @e421083458/jarvis-tts
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install jarvis-tts
What This Skill Does
Converts text to speech using Microsoft edge-tts and plays audio via macOS afplay. Supports multiple Chinese voice options including male and female Neural TTS voices. Requires network access to call the Microsoft TTS API.
Uses Microsoft Neural TTS voices which sound significantly more natural than system-level TTS alternatives.
When to use it
- Getting spoken replies from an AI assistant
- Reading long articles or documents aloud
- Setting voice reminders or notifications
- Previewing different Chinese TTS voice styles
- Generating audio output for automation scripts
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: say '好的，马上执行' in the default voice
AGENT
- 1Call jarvis-tts.sh with the text as argument
- 2edge-tts sends request to Microsoft TTS API and generates MP3 to /tmp
- 3Script checks file exists and has non-zero size
- 4afplay plays the MP3 file synchronously until complete
- 5Temporary file is deleted
OUTPUT
Audio of '好的，马上执行' plays through system speakers
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
edge-tts Python package (pip3 install edge-tts)macOS (afplay is required for playback)