Setup & Installation
openclaw skills install @szafranski/local-piper-tts-multilang-secure
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install local-piper-tts-multilang-secure
What This Skill Does
Generates audio files from text entirely offline using Piper TTS. Supports automatic language detection for 20+ languages and per-call voice selection. Self-contained setup installs Piper into an isolated virtual environment with no system-wide changes.
Produces speech locally with no API calls, no usage costs, and no data sent to external services.
When to use it
- Reading articles or documents aloud hands-free
- Adding narration to videos without cloud TTS costs
- Converting foreign-language text to speech for pronunciation reference
- Building voice interfaces for offline or air-gapped systems
- Creating audio versions of written content for accessibility
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Read this paragraph aloud using a German voice
AGENT
- 1Call status() to confirm Piper is installed and a voice model is present
- 2Call listVoices() to find installed German voice stems
- 3Call tts() with the text and the matching German voice stem
- 4Send the generated .ogg file to the user as a voice message
OUTPUT
An .ogg audio file of the paragraph spoken in German
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
ffmpeg (system binary, required for audio conversion)espeak-ng (system library required by Piper TTS)