Setup & Installation
openclaw skills install @bewareofddog/beware-piper-tts
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install beware-piper-tts
Version History
v1.0.1Feb 22, 2026 - Version note by skill developer:
No code or documentation changes detected. - Version bump only; no functional or content updates in this release.
What This Skill Does
Piper TTS converts text to speech locally using the Piper engine, generating MP3 files without any cloud calls or API keys. After a one-time setup, it works offline and delivers audio as native voice messages on supported chat platforms.
Runs entirely offline after setup, so there are no API costs, no rate limits, and no dependency on third-party TTS services.
When to use it
- Sending a spoken joke or story as a voice message in Telegram
- Getting a hands-free audio summary of a long agent response
- Receiving spoken reminders or alerts from an agent
- Hearing written content read aloud in Discord
- Delivering agent replies as voice notes instead of text
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Tell me a joke as audio
AGENT
- 1Generates the joke text
- 2Runs scripts/piper-speak.sh with the joke as input
- 3Receives the MP3 file path from script output
- 4Replies with [[audio_as_voice]] and MEDIA:<path>
OUTPUT
A native voice message with the joke delivered in the chat channel