openai-whisper

Transcribe and translate audio files locally using the Whisper CLI.

12|3|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/ApiliumCode/mayros --skill openai-whisper-apiliumcode
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/ApiliumCode/mayros/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/ApiliumCode/mayros --skill openai-whisper-apiliumcode

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine.
  • Multiple Formats: Supports various audio input formats.
  • Translation: Can translate audio from supported languages into English.
  • Use Case: Transcribe meeting recordings or voice notes securely on your local system.

Quick Start

Use whisper to transcribe the audio file located at /path/to/audio.mp3 using the medium model and output the transcription 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 files locally without an API key?

You can transcribe audio files locally without an API key by using the Whisper CLI to process speech-to-text directly on your machine. This Skill executes the whisper binary to securely convert spoken word recordings into text.

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

Yes, you need the Whisper binary installed and accessible in your system's PATH to perform local speech-to-text. This Skill acts as a wrapper for the CLI, so the underlying executable must be present in your environment.

Can I translate audio to English using local transcription?

Yes, local transcription with the Whisper CLI supports translating audio from supported languages into English. This allows you to securely generate English text content from foreign language voice notes or meeting recordings.

What is the best way to securely transcribe meeting recordings?

The best way to securely transcribe meeting recordings is using local speech-to-text processing with the Whisper CLI. By running transcription directly on your machine, you keep sensitive audio data private without relying on external APIs.

What audio formats are supported for local speech-to-text processing?

Local speech-to-text processing supports various audio input formats through the Whisper CLI. You can transcribe files like MP3s directly on your machine by specifying the file path and desired model size in your command.

Why choose local transcription over external speech-to-text APIs?

Choose local transcription for privacy-focused audio processing, as it transcribes speech-to-text directly on your machine without external API calls. This ensures secure handling of sensitive meeting recordings and voice notes.