Aj Openai Whisper
PassAudited by ClawScan on May 1, 2026.
Overview
This is a simple instruction-only Whisper CLI skill whose local transcription behavior matches its description, with only expected external install/model-download considerations.
This skill appears safe for its stated purpose. Before installing, understand that it depends on the Homebrew `openai-whisper` package and may download Whisper model files to your local cache; review the audio file paths and output locations when using it.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing the skill may require installing the Whisper CLI package through Homebrew.
The skill relies on an external Homebrew package to provide the CLI. This is expected for the skill's purpose, but it means installation depends on that package's provenance and behavior.
brew | formula: openai-whisper | creates binaries: whisper
Install only if you are comfortable trusting the Homebrew `openai-whisper` package and your local package manager.
The agent can help run local Whisper commands against audio files you specify.
The skill's core behavior is running a local CLI command. This is disclosed and directly aligned with local speech-to-text functionality.
Use `whisper` to transcribe audio locally.
Review the audio path and output directory before running transcription commands.
First use may download model files and use local disk space.
The first use may fetch model files and store them locally. This is disclosed and normal for Whisper, but it is still an external download and local persistence.
Models download to `~/.cache/whisper` on first run.
Ensure you have sufficient disk space and are comfortable with Whisper downloading model files to your local cache.