Openai Whisper
Transcribe voice memos, meetings, and audio locally with the Whisper CLI so agents can work from text without a cloud STT API key.
Install
npx skills add https://github.com/steipete/clawdis --skill openai-whisperWhat is this skill?
- Local transcription via `whisper` CLI—no OpenAI API key required
- Quick recipes for txt and srt output with `--model` and `--output_dir`
- `--task translate` path for non-English audio to English text
- Documents model cache at `~/.cache/whisper` on first download
- Notes default `turbo` model on the documented install with smaller models for speed
Adoption & trust: 3.1k installs on skills.sh; 378k GitHub stars; 3/3 security scanners passed (skills.sh audits).
Recommended Skills
Microsoft Foundrymicrosoft/azure-skills
Azure Aimicrosoft/azure-skills
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Lark Eventlarksuite/cli
Running Claude Code Via Litellm Copilotxixu-me/skills
Setup Matt Pocock Skillsmattpocock/skills
Journey fit
Primary fit
Canonical shelf is Build integrations because the skill wires a local binary into agent workflows for speech-to-text pipelines. Integrations subphase matches optional `whisper` CLI install (e.g. Homebrew) and command recipes agents invoke on audio files.
Common Questions / FAQ
Is Openai Whisper safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Openai Whisper
# Whisper (CLI) Use `whisper` to transcribe audio locally. Quick start - `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .` - `whisper /path/audio.m4a --task translate --output_format srt` Notes - Models download to `~/.cache/whisper` on first run. - `--model` defaults to `turbo` on this install. - Use smaller models for speed, larger for accuracy.