← Back to Skills Marketplace
Faster Whisper Transcription
by
Khalid Almuraee
· GitHub ↗
· v1.0.0
1069
Downloads
0
Stars
4
Active Installs
1
Versions
Install in OpenClaw
/install faster-whisper-transcribe
Description
Transcribes local voice messages to text using Faster Whisper models for fast, privacy-focused speech recognition on audio files.
README (SKILL.md)
Voice Transcription Skill
Transcribes voice messages using Faster Whisper (local, privacy-first).
Requirements
pip3 install --break-system-packages faster-whisper
Usage
# Transcribe a voice file
voice-transcribe /path/to/audio.ogg
# Or use with media path
voice-transcribe ~/.openclaw/media/inbound/file_xxx.ogg
Models
tiny- Fastest, lowest accuracy (default)base- Balancedsmall- Better accuracymedium- High accuracy (requires more RAM)
Output
Returns transcribed text from voice messages.
Usage Guidance
This skill's goal (local transcription using Faster Whisper) is reasonable, but the instructions are incomplete and ask you to install a third-party pip package into your system Python using --break-system-packages. Before installing or running it, consider: 1) Verify the faster-whisper package source (PyPI project page, GitHub repo) and inspect its code or release artifacts; 2) Avoid --break-system-packages — install inside a virtualenv, conda env, or container to isolate changes; 3) Confirm whether the 'voice-transcribe' CLI is provided by that package and what network or model downloads it will perform (model downloads can be large and may contact external servers); 4) Test installation and transcription in a sandboxed VM/container first to ensure no unexpected behavior or data exfiltration; 5) If you cannot verify the package/source, do not run the pip install on a production machine. If you want, provide the package source URL or the exact command the agent will run and I can re-evaluate with more detail.
Capability Analysis
Type: OpenClaw Skill
Name: faster-whisper-transcribe
Version: 1.0.0
The skill bundle is classified as suspicious due to the use of `pip3 install --break-system-packages` in `SKILL.md`. While installing a legitimate library (`faster-whisper`), this flag bypasses Python's PEP 668 safety mechanism, which can lead to system instability or conflicts by installing packages into the system Python environment. This represents a vulnerability or risky practice, but not direct evidence of malicious intent like data exfiltration or backdoor installation.
Capability Assessment
Purpose & Capability
Name/description align with using Faster Whisper for local transcription and the SKILL.md asks to pip-install faster-whisper and run a transcription command, which is generally consistent. However the skill provides no code and no explicit source for the 'voice-transcribe' command it instructs you to run, leaving a gap between claimed capability and provided artifacts.
Instruction Scope
Instructions tell the agent/user to run 'pip3 install --break-system-packages faster-whisper' and then run 'voice-transcribe /path/to/audio.ogg'. That install step causes arbitrary remote code to be installed into the system Python environment (the --break-system-packages flag is potentially destructive), and the SKILL.md does not explain where the 'voice-transcribe' CLI comes from or what it will do with the audio (download models, network activity, file writes). The instructions therefore are incomplete and grant broad discretion to install/run third-party code.
Install Mechanism
This is an instruction-only skill, but it explicitly asks to pip-install a third-party package from the network. Installing a pip package is a moderate-risk operation because it downloads and executes code from PyPI (or whatever index pip resolves to). The use of --break-system-packages increases risk by allowing modification of the system Python environment instead of suggesting a virtualenv/containerized install.
Credentials
The skill requests no environment variables, credentials, or config paths. There is no direct request for unrelated secrets or system credentials.
Persistence & Privilege
The skill does not request always:true, does not declare installs that modify other skills or system-wide settings in the registry metadata, and is user-invocable only. No elevated persistence is requested by the manifest.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install faster-whisper-transcribe - After installation, invoke the skill by name or use
/faster-whisper-transcribe - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the Voice Transcription Skill.
- Transcribes audio files locally using Faster Whisper for privacy.
- Supports multiple model sizes: tiny, base, small, medium.
- Simple command-line usage for voice file transcription.
- Outputs transcribed text from voice messages.
Metadata
Frequently Asked Questions
What is Faster Whisper Transcription?
Transcribes local voice messages to text using Faster Whisper models for fast, privacy-focused speech recognition on audio files. It is an AI Agent Skill for Claude Code / OpenClaw, with 1069 downloads so far.
How do I install Faster Whisper Transcription?
Run "/install faster-whisper-transcribe" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Faster Whisper Transcription free?
Yes, Faster Whisper Transcription is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Faster Whisper Transcription support?
Faster Whisper Transcription is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Faster Whisper Transcription?
It is built and maintained by Khalid Almuraee (@kalmuraee); the current version is v1.0.0.
More Skills