Setup & Installation
openclaw skills install @huixionghexiyi/free-groq-voice
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install free-groq-voice
What This Skill Does
Uses Groq's free Whisper API tier to transcribe audio files and voice messages into text. Supports 50+ languages and common audio formats including OGG, MP3, WAV, M4A, and WebM. No payment or credit card required.
Groq's free tier uses the same whisper-large-v3 model as paid OpenAI Whisper but at $0 cost and faster inference speeds.
When to use it
- Transcribing voice messages from Feishu or Telegram
- Converting meeting recordings to written notes
- Batch processing a folder of audio files
- Enabling voice input for non-English speakers
- Adding accessibility transcription to recorded content
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User sends a voice message and asks for transcription
AGENT
- 1Receives audio file path from user message
- 2Sends file to Groq API endpoint with configured API key and language hint
- 3Receives transcription response from whisper-large-v3 model
- 4Returns transcribed text to user
OUTPUT
"You said: 'Meeting starts at 3pm, please review the proposal beforehand'"
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
Groq API key from console.groq.com (free, no credit card)HTTP proxy configured if accessing from a restricted region