openai-whisper

Transcribe audio files locally using the Whisper CLI.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/frankhli843/gemmahermes --skill openai-whisper-frankhli843
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/frankhli843/gemmahermes/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/frankhli843/gemmahermes --skill openai-whisper-frankhli843

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Whisper (CLI) enables local transcription of audio without sending data to external services, preserving privacy and reducing latency.

Core Features & Use Cases

  • Local speech-to-text transcription using the Whisper CLI.
  • Supports multiple audio formats and languages with offline processing.
  • Use Case: transcribe meetings, podcasts, or video captions on a lightweight, offline workflow.

Quick Start

Run whisper on an audio file to generate a transcription locally.

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 relying on external APIs?

The Whisper CLI supports offline transcription of multiple audio formats for meetings, podcasts, or video captions. It processes speech locally to generate text without sending data to external services, ensuring privacy and low latency.

Does offline speech-to-text transcription work with different languages and audio formats?

Offline speech-to-text transcription with Whisper CLI supports multiple audio formats and languages. You can adjust language and model settings via command-line flags to process various audio files locally.

What do I need to run local audio transcription with the Whisper CLI?

Running local audio transcription requires local Whisper binaries installed on your machine. The Skill uses default model behavior and operates entirely offline without external API dependencies.

Can I adjust the model or language for offline transcription tasks?

Yes, you can adjust model and language for offline transcription tasks using optional command-line flags in the Whisper CLI. This allows customization while maintaining local, private audio processing.

What is the best way to transcribe podcasts or meetings without sending data to external services?

Using the Whisper CLI for local speech-to-text conversion is the best way to transcribe podcasts or meetings privately. This offline workflow processes audio on your machine, avoiding external APIs and protecting data.

When should I avoid using local offline transcription?

Avoid local offline transcription if you lack local Whisper binaries or sufficient compute resources. If your workflow requires real-time cloud API integration rather than processing local audio files, external transcription services may be more suitable.