Labsco
firecrawl logo

openai-whisper

★ 3

by firecrawl · part of firecrawl/openclaw

Transcribes or translates audio into text entirely on your own machine using the local Whisper CLI, with no API key or cloud service required.

🔥🔥🔥✓ VerifiedFreeQuick setup
#voice
🔌 Needs the Whisper CLI. Set that up first — this skill doesn't include it. One of 59 skills in the firecrawl/openclaw package.

WHEN YOUR AGENT SHOULD USE IT

A QUICK BOUNDARY

USE FOR

  • Transcribe a local audio file into a text or subtitle file.
  • Translate audio spoken in another language into English text.
  • Trade transcription speed for accuracy by choosing a smaller or larger model.

This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.

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.