openai-whisper

Transcribe local audio files into text using OpenAI Whisper CLI.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/PotLock/foxfang --skill openai-whisper-potlock
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/PotLock/foxfang/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/PotLock/foxfang --skill openai-whisper-potlock

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio locally into text without relying on external APIs, ensuring privacy and offline operation.

Core Features & Use Cases

  • Local CLI transcription using OpenAI Whisper; supports multiple models and languages.
  • No API key required; data stays on device.
  • Useful for podcasters, researchers, journalists who need quick, private transcripts.

Quick Start

Transcribe an audio file by running Whisper on your machine to generate a text transcript.

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?

You can transcribe audio locally by running the Whisper CLI on your machine, which processes common audio formats into text without requiring an API key and keeps all data on your device for privacy.

What is offline speech-to-text and when do I need it?

Offline speech-to-text converts audio to text without an internet connection. You need it for privacy-sensitive data or when working in restricted environments where sending audio to external transcription APIs is not allowed.

Do I need an API key to use local Whisper transcription?

No, local Whisper transcription does not require an API key. The process runs entirely on your local machine using a locally installed whisper binary, ensuring your audio data stays on your device.

Can I use local transcription for generating captions from common audio formats?

Yes, local transcription supports caption generation from common audio formats. By running the Whisper CLI offline, you can select different models and languages to generate text transcripts and captions directly on your machine.

What are the limitations of offline transcription with the Whisper CLI?

Offline transcription with the Whisper CLI requires a locally installed whisper binary and depends entirely on your local machine's processing power. Model selection impacts accuracy and speed, but no external API scaling is available.