# Openai Whisper Local

> Local speech-to-text transcription with the Whisper CLI. No API key required -- runs entirely offline with configurable model sizes.

- Skill: `yunseo-kim/openai-whisper-local` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yunseo-kim/openai-whisper-local`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yunseo-kim/openai-whisper-local/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- License: Sustainable Use License 1.0
- Author: yunseo-kim (https://skillmd.com/u/yunseo-kim)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yunseo-kim/openai-whisper-local

---


# 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.