openai-whisper

Transcribe and translate audio files locally using the Whisper CLI.

2|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/FatBy/DD-OS --skill openai-whisper-fatby
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/FatBy/DD-OS/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/FatBy/DD-OS --skill openai-whisper-fatby

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a local, privacy-focused solution for converting spoken audio into written text without relying on external APIs or requiring an API key.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • Translation: Supports translating audio from various languages into English text.
  • Use Case: You need to transcribe a confidential meeting recording or a long lecture without sending sensitive audio data to a third-party service.

Quick Start

Use the openai-whisper skill to transcribe the audio file located at /path/to/meeting.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 locally without using external APIs?

Local speech-to-text transcription can be performed directly on your machine using the Whisper CLI, converting spoken audio into written text without relying on external APIs or requiring an API key. This ensures secure audio processing for sensitive recordings.

Do I need to install the Whisper executable to use local speech-to-text transcription?

Yes, local speech-to-text transcription requires the Whisper executable to be installed and available in your system's PATH before you can transcribe audio files or translate spoken languages into English text.

Can I translate audio from various languages into English text locally?

Yes, local speech-to-text translation supports translating audio from various languages into English text directly on your machine, ensuring privacy for confidential meeting recordings or long lectures without sending data to third-party services.

What is the best way to transcribe a confidential meeting recording securely?

The best way to securely transcribe a confidential meeting recording is using local speech-to-text transcription, which processes the audio file directly on your machine via the Whisper CLI without sending sensitive audio data to external third-party services.

How do I transcribe an audio file using the medium model with Whisper?

To transcribe an audio file using the medium model, direct the local speech-to-text transcription tool to process your specified audio file path, selecting the medium model within the Whisper CLI for balanced accuracy and processing speed.

Are there limitations when processing long lectures for content creation locally?

Processing long lectures for content creation locally depends entirely on your machine's computational resources, as local speech-to-text transcription uses the Whisper CLI directly rather than external cloud APIs, potentially requiring significant processing time for extended audio files.