openai-whisper-local

Transcribe audio files to text locally using the Whisper CLI.

1|1|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/yunseo-kim/agent-toolbox --skill openai-whisper-local
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-local
Source: https://github.com/yunseo-kim/agent-toolbox/tree/main/catalog/skills/openai-whisper-local
Command: npx skills add https://github.com/yunseo-kim/agent-toolbox --skill openai-whisper-local

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a local, offline solution for converting audio files into text, eliminating the need for an internet connection or API keys.

Core Features & Use Cases

  • Offline Transcription: Transcribe audio files directly on your machine without relying on cloud services.
  • Configurable Models: Supports various Whisper model sizes, allowing you to balance speed and accuracy.
  • Use Case: Transcribe meeting recordings or voice notes securely on your local system, ensuring data privacy.

Quick Start

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

Frequently Asked Questions about openai-whisper-local

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 converts audio files to text directly on your machine. This Skill uses the Whisper CLI to process audio offline, ensuring data privacy without cloud services or API keys.

Can I balance transcription speed and accuracy with offline Whisper models?

Yes, offline Whisper transcription supports configurable model sizes. You can select different models to balance processing speed and transcription accuracy for your audio files.

What is the best way to securely transcribe meeting recordings without uploading them?

Secure offline transcription processes sensitive meeting recordings directly on your local system. By using the local Whisper CLI, you eliminate risks associated with uploading private audio files to cloud services.

Do I need API keys to perform speech-to-text transcription on my machine?

No, local speech-to-text transcription does not require API keys. By running the Whisper CLI offline on your local system, you generate text transcriptions from audio files independently of external service authentication.

How do I output my local audio transcription to a text file?

Local audio transcription outputs directly to a text file. You specify the output format when running the Whisper CLI on your local machine to save transcribed speech content from your audio file.