Use Case
Voice Reply is a powerful AI agent skill that extends your assistant with new capabilities. Local text-to-speech using Piper voices via sherpa-onnx. 100% offline, no API keys required. Use when user asks for a voice reply, audio response, spoken answer, or wants to hear something read aloud. Supports multiple languages including German (thorsten) and English (ryan) voices. Outputs Telegram-compatible voice notes with [[audio_as_voice]] tag. This guide walks you through installing Voice Reply, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Voice Reply: npx clawhub@latest --dir ~/.claude/skills install voice-reply
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to design & creative to trigger Voice Reply
Review the output and refine your prompt for better results
Combine Voice Reply with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Voice Reply
Help me get started with Voice Reply
What can Voice Reply do for my design & creative workflow?
Show me an example of using Voice Reply
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install voice-replyOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install voice-replyβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/voice-reply/π‘Extract and place the folder at the path above, then restart your agent.