Openai Whisper

Local speech-to-text with the Whisper CLI (no API key).

Peter Steinberger

@steipete

What This Skill Does

Transcribes audio files to text locally using OpenAI's Whisper CLI, with no API key or internet required. Supports multiple output formats (txt, srt, vtt) and model sizes for speed vs. accuracy trade-offs.

Replaces cloud-based speech-to-text services by running entirely offline on your own machine, eliminating API costs and privacy concerns.

When to Use It

  • Transcribe meeting recordings or lecture audio to searchable text
  • Generate subtitles (SRT/VTT) for video content
  • Translate non-English speech to English text in one command
  • Convert voice memos or dictation notes to plain text
  • Process sensitive audio files that cannot be sent to cloud APIs
  • Batch-transcribe multiple audio files with a single command

Install

$ openclaw skills install @steipete/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.

Top skills in this category