mcpField
O
openai-whisper

openai-whisper

github.com/openclawCreative & media393.3k7.2k installsUpdated today
Repository

About openai-whisper

openai-whisper is a command-line tool for transcribing audio locally, for users who need text or subtitles from audio. It offers selectable models and supports translation tasks and multiple output formats.

Key features

  1. 01Transcribe audio locally
  2. 02Choose a transcription model
  3. 03Output TXT or SRT
  4. 04Run audio translation tasks

Use cases

  1. 01Transcribe an MP3 into a text file
  2. 02Translate M4A audio and create subtitles

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openclaw/openclaw --skill openai-whisper

After installing, type/openai-whisperin Claude Code to confirm it loaded.

Details

From the project README

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.

Comments

Markdown supported