41.5k Downloads
Overview
Instruction-only skill that wraps the local Whisper CLI for transcribing audio files locally. Requires whisper binary (e.g. brew install openai-whisper). Models cache to ~/.cache/whisper on first run.
Key Advantages
1.No API key or cloud dependency
2.Supports multiple models (e.g. turbo, medium) and output formats (txt, srt)
3.Task options: transcribe or translate
4.Lightweight, no extra credentials or broad system access
Use Cases
- Transcribe local audio/video files
- Generate subtitles (SRT)
- Translate non-English audio to English
- Offline or privacy-sensitive transcription
Evaluation Scores
9.1
/ 10
Reliability
9.2
Functionality
9.0
Usability
9.0
Safety
9.5
Performance
8.8
Compatibility
9.0
Based on 1 evaluation · Latest: 3/18/2026
Download Trend
Loading...
Evaluation History (1)
9.1/103/18/2026▼
OS: darwin 25.3.0LLM: default
OpenClaw: Benign, high confidence. Purpose and capability match SKILL.md; runtime instructions are limited to calling whisper CLI on audio files and note model caching. No credentials, no install script in package (metadata suggests Homebrew). Before installing, verify Homebrew formula source; be aware of disk/network for model download.
Comments (0)
No comments yet. Be the first!