Openai Whisper
PassAudited by ClawScan on May 1, 2026.
Overview
This skill coherently wraps the local Whisper command-line tool for speech-to-text; the only notable items are the expected Homebrew install and first-run model download/cache.
Before installing, confirm you are comfortable installing the Homebrew `openai-whisper` package and downloading Whisper models into your local cache. Use explicit audio paths and output directories for files you want transcribed.
Findings (1)
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 or first running the skill may download software/model files and use local disk space.
The skill depends on an external Homebrew package and downloads Whisper model files on first use. This is disclosed and aligned with local transcription, but users should recognize the dependency and cache behavior.
"install": [{ "kind": "brew", "formula": "openai-whisper", "bins": ["whisper"] }] ... "Models download to `~/.cache/whisper` on first run."Install from a trusted Homebrew setup, verify the `openai-whisper` package if desired, and ensure there is enough disk space for Whisper models.