mcpField
O
openai-whisper

openai-whisper

github.com/sundial-orgCreative & media67041 installsUpdated 34w ago
Repository

About openai-whisper

A CLI skill for transcribing audio locally with Whisper. It supports text transcription and translation output, with selectable models that trade speed against accuracy.

Key features

  1. 01Local audio transcription
  2. 02Audio translation task
  3. 03TXT and SRT output formats
  4. 04Selectable Whisper models

Use cases

  1. 01Transcribe an audio file to text
  2. 02Create subtitles from audio
  3. 03Translate audio into subtitle output

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sundial-org/awesome-openclaw-skills --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