openai-whisper

Transcribe audio files to text using the local Whisper CLI engine.

6|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/me2Doc/friendlyclaw --skill openai-whisper-me2doc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/me2Doc/friendlyclaw/tree/main/body/skills/openai-whisper
Command: npx skills add https://github.com/me2Doc/friendlyclaw --skill openai-whisper-me2doc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper.

What problem does it solve?

This skill removes the need for cloud-based transcription services by enabling high-quality, local speech-to-text processing directly on your machine.

Core Features & Use Cases

  • Local Transcription: Converts audio files to text without sending data to external APIs.
  • Multi-Language Support: Handles both transcription and translation tasks seamlessly.
  • Use Case: Quickly transcribe long meeting recordings or voice memos into text files for documentation without privacy concerns or subscription costs.

Quick Start

Use the openai-whisper skill to transcribe the audio file located at path/to/recording.mp3 using the medium model.

Frequently Asked Questions about openai-whisper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio files to text locally without using cloud APIs?

To transcribe audio files locally, you can use the openai-whisper skill which processes speech-to-text directly on your machine. It converts your recordings into text files without sending data to external APIs, ensuring privacy.

Does local speech-to-text transcription work for multi-language audio translation?

Yes, local speech-to-text transcription supports multi-language audio translation. The skill handles both transcription and translation tasks seamlessly, allowing you to convert foreign language recordings into text offline.

Do I need to install the whisper binary to use this local transcription skill?

Yes, you need the whisper binary installed on your system path to use this local transcription skill. The skill relies on the local Whisper CLI engine to execute offline speech-to-text processing.

What is the best way to transcribe long meeting recordings offline?

The best way to transcribe long meeting recordings offline is using the openai-whisper skill with a medium model. It processes extended audio files locally, converting voice memos into text files for documentation without subscription costs.

Can I use local transcription for diverse audio formats?

Yes, you can use local transcription for diverse audio formats. The skill supports processing various audio file types, converting them into text using the local Whisper CLI engine for offline documentation and analysis.