openai-whisper

Transcribe spoken audio into text locally using the Whisper CLI.

5|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/gabrielkoerich/skills --skill openai-whisper-gabrielkoerich
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/gabrielkoerich/skills/tree/main/openai-whisper
Command: npx skills add https://github.com/gabrielkoerich/skills --skill openai-whisper-gabrielkoerich

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes speech locally on your device without sending audio to external services.

Core Features & Use Cases

  • Local transcription using Whisper CLI
  • Supports translation mode and output formatting (txt, srt, json)
  • No API key required; works offline to protect privacy

Quick Start

Run whisper on your audio file with a chosen model to generate a transcript 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 speech to text locally without sending audio to cloud services?

Local speech-to-text transcription runs directly on your device using the Whisper CLI, converting spoken audio into text files completely offline without cloud services. This protects privacy for meetings, lectures, and personal notes.

Do I need an API key to run offline transcription with Whisper?

No API key is required for offline transcription. The Whisper CLI operates entirely locally without external cloud services, ensuring no authentication or internet connection is needed to process audio files.

What output formats does local transcription support?

Local transcription supports configurable output formats including txt, srt, and json. The Whisper CLI generates these text files locally, allowing you to choose the format that best fits your transcription needs.

Can I translate spoken audio into text locally using Whisper?

Yes, Whisper supports translation mode for transcribing spoken audio locally. The CLI processes audio files offline and can translate speech into text while generating output in your chosen format.

What do I need installed to run local speech-to-text transcription?

You need the Whisper CLI installed on your device to run local speech-to-text transcription. Once installed, the tool works offline without requiring API keys or cloud services to process audio files.

Is local transcription suitable for processing meeting recordings?

Local transcription is suitable for meetings, lectures, and personal notes. The Whisper CLI processes these audio recordings offline, ensuring sensitive spoken content remains private on your device without cloud exposure.