openai-whisper

Transcribe audio files locally using the OpenAI Whisper CLI.

Updated Jan 20, 2026
One-click install
npx skills add https://github.com/Xyxy1722/Agent-skills --skill openai-whisper-xyxy1722
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Xyxy1722/Agent-skills/tree/main/usage/openai-whisper
Command: npx skills add https://github.com/Xyxy1722/Agent-skills --skill openai-whisper-xyxy1722

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a local speech-to-text transcription service, eliminating the need for an internet connection or API keys for audio transcription.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • No API Key Required: Operates entirely offline, ensuring privacy and avoiding external service costs.
  • Use Case: Transcribe meeting recordings or voice notes without uploading sensitive audio to a cloud service.

Quick Start

Use whisper to transcribe the audio file located at /path/to/my/audio.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 an internet connection?

Local speech-to-text transcription can be performed directly on your machine using the OpenAI Whisper CLI. It processes audio files entirely offline, requiring no internet connectivity or API keys to generate text transcripts.

Do I need an API key to use Whisper for speech-to-text transcription?

No API key is required for speech-to-text transcription using the local Whisper CLI. The process operates completely offline on your machine, ensuring data privacy and avoiding any external service costs or authentication requirements.

How do I transcribe meeting recordings without uploading sensitive audio to a cloud service?

You can transcribe sensitive meeting recordings offline using the local Whisper CLI. By processing audio files directly on your machine, the speech-to-text transcription maintains privacy without uploading data to external cloud services.

What are the requirements to run local speech-to-text transcription with Whisper?

To run local speech-to-text transcription, the 'whisper' binary must be installed and available in your system's PATH. This local environment setup allows the CLI to process audio files offline without external dependencies.

Can I use the Whisper CLI to transcribe voice notes on my computer?

Yes, the Whisper CLI performs local speech-to-text transcription for voice notes. By executing the command with an audio file path and a model like medium, it processes the audio directly on your computer to deliver text output.