← Back to Skills Marketplace
Groq Whisper
by
Brice Thrower
· GitHub ↗
· v1.0.1
· MIT-0
186
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install groq-whisper
Description
Transcribe audio files using Groq's Whisper API (whisper-large-v3). Fast cloud-based speech-to-text with no local model required. Use when receiving voice me...
README (SKILL.md)
Groq Whisper
Cloud speech-to-text via Groq's Whisper API. No local model, no GPU, no fan spin.
Setup
- Get a free API key at
console.groq.com - Store it:
Or setmkdir -p ~/.config/groq echo '{"api_key":"gsk_your_key_here"}' > ~/.config/groq/credentials.json chmod 600 ~/.config/groq/credentials.jsonGROQ_API_KEYenv var.
Usage
# Transcribe an audio file
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg
# Specify language (default: en)
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg es
When to use
Call this script whenever you receive an audio/voice message attachment. Pass the file path directly — Groq handles ogg, mp3, wav, m4a, webm, and flac natively. No format conversion needed.
Details
- Model: whisper-large-v3 (best accuracy)
- Speed: Faster than real-time (typically \x3C2s for a 5-minute clip)
- Cost: Free tier available, no credit card required
- Privacy: Groq does not retain input data or train on it
- Requires:
curl,jq, Groq API key
Usage Guidance
This skill appears to do exactly what it says: it uploads a local audio file to Groq's transcription API and prints the returned text. Before installing, confirm you are comfortable sending audio to Groq (do not use for sensitive audio if that is a concern), keep your GROQ_API_KEY private (store it with strict file permissions or as an env var), and ensure curl and jq are installed. You can review the included scripts (transcribe.sh) yourself — it only reads the provided file and the optional credentials file and calls api.groq.com. Note the agent can call the skill autonomously (normal default) but the skill is not force-enabled (always:false). If you operate in a multi-user/shared environment, avoid placing keys in globally readable locations.
Capability Analysis
Type: OpenClaw Skill
Name: groq-whisper
Version: 1.0.1
The skill is a legitimate utility for transcribing audio files using the Groq Whisper API. The bash script (scripts/transcribe.sh) correctly handles API key retrieval from environment variables or a local config file and uses standard tools (curl, jq) to interact with the official Groq endpoint (api.groq.com). No malicious behavior, data exfiltration, or prompt injection attempts were found.
Capability Assessment
Purpose & Capability
Name/description match the included script and instructions. Required tools (curl, jq) and the optional GROQ_API_KEY/credentials file are exactly what a cloud transcription helper needs.
Instruction Scope
Runtime instructions and the script only read the provided audio file and an optional credentials file (~/.config/groq/credentials.json). They post the audio to Groq's API and parse the JSON response; there is no unexpected file access or external endpoints beyond api.groq.com.
Install Mechanism
No install spec — instruction-only plus a small bundled bash script. Nothing is downloaded or executed from untrusted URLs and no archives are extracted.
Credentials
Only an optional GROQ_API_KEY (or local credentials file) is used, which is proportionate to the skill's purpose. No other secrets, unrelated credentials, or config paths are requested.
Persistence & Privilege
The skill does not request permanent/enforced presence (always:false) and does not modify agent or system-wide settings. It behaves as a normal invocation-only helper.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install groq-whisper - After installation, invoke the skill by name or use
/groq-whisper - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Added declared dependencies (curl, jq) and GROQ_API_KEY env var to metadata for VirusTotal/ClawHub compliance
v1.0.0
Initial release: cloud speech-to-text via Groq Whisper API (whisper-large-v3), no local model required
Metadata
Frequently Asked Questions
What is Groq Whisper?
Transcribe audio files using Groq's Whisper API (whisper-large-v3). Fast cloud-based speech-to-text with no local model required. Use when receiving voice me... It is an AI Agent Skill for Claude Code / OpenClaw, with 186 downloads so far.
How do I install Groq Whisper?
Run "/install groq-whisper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Groq Whisper free?
Yes, Groq Whisper is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Groq Whisper support?
Groq Whisper is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Groq Whisper?
It is built and maintained by Brice Thrower (@directorvector); the current version is v1.0.1.
More Skills