openai-whisper

Transcribe local audio files into text using the Whisper CLI.

1|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/pablomat555/eggent-ai --skill openai-whisper-pablomat555
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/pablomat555/eggent-ai/tree/main/bundled-skills/openai-whisper
Command: npx skills add https://github.com/pablomat555/eggent-ai --skill openai-whisper-pablomat555

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Whisper CLI enables local speech-to-text transcription without relying on external APIs, preserving privacy and reducing data exposure.

Core Features & Use Cases

  • Local transcription of audio files (mp3, wav, m4a) using the Whisper CLI.
  • Optional translation and model-variant support with offline caching of models to improve startup times.
  • Suitable for privacy-conscious workflows like interviews, lectures, and accessibility tasks, across personal or professional contexts.

Quick Start

Run whisper on a local audio file to generate a transcription with your preferred 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 locally without sending data to an external API?

Transcribe audio locally by running the Whisper CLI on your audio files. This offline transcription method processes mp3, wav, and m4a formats directly on your machine, preserving privacy without requiring API keys.

Can I use Whisper CLI for offline transcription of interviews and lectures?

Yes, offline transcription with Whisper CLI is suitable for privacy-conscious workflows like interviews and lectures. It processes audio locally and supports optional translation across common audio formats.

Do I need an API key to transcribe audio files with Whisper?

No, you do not need an API key to transcribe audio files. The Whisper CLI operates entirely locally, enabling private speech-to-text processing without relying on external services.

What audio formats are supported for local transcription with Whisper CLI?

Local transcription with Whisper CLI supports common audio formats including mp3, wav, and m4a. This allows you to process various audio files for interviews and podcasts directly on your device.

How does Whisper CLI handle model selection and offline caching?

Whisper CLI supports model-variant selection for transcription and uses offline caching of models to improve startup times. This enables flexible local processing tailored to your accuracy requirements.

What is the best way to get text from an audio file privately?

The best way to get text from audio privately is local transcription using the Whisper CLI. It converts audio files to text offline, ensuring data privacy without sending sensitive recordings to external APIs.