openai-whisper

Transcribes audio files into text using the local Whisper CLI engine.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/tedtv1007-ctrl/milk-skills-library --skill openai-whisper-tedtv1007-ctrl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/tedtv1007-ctrl/milk-skills-library/tree/main/openai-whisper
Command: npx skills add https://github.com/tedtv1007-ctrl/milk-skills-library --skill openai-whisper-tedtv1007-ctrl

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 Processing: Transcribes audio files without sending data to external servers, ensuring complete privacy.
  • Flexible Tasking: Supports both direct transcription and language translation tasks.
  • Use Case: Use this to quickly generate meeting transcripts from recorded audio files or to translate foreign language voice memos into text without incurring API costs.

Quick Start

Use the whisper skill to transcribe the audio file located at path/to/recording.mp3 using the medium model and save the output as a text file.

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 to text locally without sending data to external servers?

You can transcribe audio to text locally by running the openai-whisper CLI engine offline, which processes speech-to-text conversion directly on your machine to ensure complete data privacy.

Can I use the Whisper CLI to translate foreign language audio files into text?

Yes, the Whisper CLI supports both direct speech-to-text transcription and language translation tasks, allowing you to convert foreign language voice memos into text offline.

Do I need to install the openai-whisper binary via Homebrew to execute local transcription tasks?

Yes, you must install the openai-whisper binary via Homebrew to execute local transcription tasks, as this Skill relies entirely on the local Whisper CLI engine to process audio files.

What is the best way to generate meeting transcripts from recorded audio files without incurring API costs?

The best way to generate meeting transcripts without API costs is using local speech-to-text processing with the Whisper CLI, which transcribes recorded audio files into text offline.

Does local speech-to-text processing with Whisper work offline for various audio formats?

Yes, local speech-to-text processing with Whisper works in offline environments and supports speech-to-text conversion for various audio formats without requiring an internet connection.