Use Case
speech-recognition is a powerful AI agent skill that extends your assistant with new capabilities. Universal speech recognition skill. Supports multiple audio formats (ogg/mp3/wav/m4a) and uses the silicon-based mobile SenseVoice API for speech-to-text. Triggered when the user sends a voice message, audio file, or audio needs to be transcribed. This guide walks you through installing speech-recognition, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install speech-recognition: npx clawhub@latest --dir ~/.claude/skills install speech-recognition
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to design & creative to trigger speech-recognition
Review the output and refine your prompt for better results
Combine speech-recognition with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing speech-recognition
Help me get started with speech-recognition
What can speech-recognition do for my design & creative workflow?
Show me an example of using speech-recognition
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install speech-recognitionOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install speech-recognitionβ 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/speech-recognition/π‘Extract and place the folder at the path above, then restart your agent.