← Back to Skills Marketplace
6368
Downloads
2
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install audio
Description
Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows.
Usage Guidance
Before installing, treat cloud transcription as third-party processing of potentially sensitive recordings, keep API tokens out of shell history and source control, and install optional Python/Conda tools in a dedicated virtual environment or container with reviewed package versions where possible.
Capability Analysis
Type: OpenClaw Skill
Name: audio
Version: 1.0.1
The skill bundle is classified as suspicious due to significant shell injection vulnerabilities. Specifically, the use of `ffmpeg -f concat -safe 0` in `commands.md` and `podcast.md` allows arbitrary file paths in the concatenation list, posing a risk if the agent constructs this list from unsanitized user input. Additionally, other shell commands involving command substitution and arithmetic (`$()`, `bc`) in `commands.md` and `podcast.md` could lead to arbitrary code execution if user-provided input is not properly sanitized by the OpenClaw agent before being passed to the shell.
Capability Assessment
Credentials
The requested environment use is proportionate: local audio files, FFmpeg/ffprobe, optional local transcription tools, and explicit optional API workflows for transcription or diarization.
Install Mechanism
The skill documents common pip and conda install commands for optional transcription tools without version pins or hashes. This is common for instructional skills but users should install in an isolated environment and verify package provenance.
Instruction Scope
The scope says cloud services are not accessed without the user knowing, and the transcription guide labels AssemblyAI and Deepgram as API-based; however, it could more explicitly warn that audio or transcript data may leave the user's environment when API services are used.
Persistence & Privilege
No artifact-backed evidence shows persistence, privilege escalation, background services, memory writes, hidden tool modification, destructive behavior, or automatic execution beyond user-directed commands.
Purpose & Capability
The skill provides Markdown guidance for FFmpeg audio processing, loudness normalization, podcast workflows, and transcription of user-provided audio files; these capabilities match its stated purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install audio - After installation, invoke the skill by name or use
/audio - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Declare required binaries (ffmpeg, ffprobe), add requirements section with optional deps, add explicit scope
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Audio?
Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows. It is an AI Agent Skill for Claude Code / OpenClaw, with 6368 downloads so far.
How do I install Audio?
Run "/install audio" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Audio free?
Yes, Audio is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Audio support?
Audio is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Audio?
It is built and maintained by Iván (@ivangdavila); the current version is v1.0.1.
More Skills