openai-whisper

Transcribe local audio files to text using Whisper's CLI.

Updated Feb 13, 2026
One-click install
npx skills add https://github.com/jonnytacos8/closed_claw --skill openai-whisper-jonnytacos8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/jonnytacos8/closed_claw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/jonnytacos8/closed_claw --skill openai-whisper-jonnytacos8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local transcription using Whisper's CLI enables turning speech into text on-device, without needing API keys or cloud services.

Core Features & Use Cases

  • Transcribes audio locally using Whisper CLI to generate text without cloud processing.
  • Supports multiple models and output formats for flexible transcription in privacy-aware workflows.
  • Use Cases: transcribing podcasts, meetings, lectures, and video content for quick text extraction.

Quick Start

Transcribe a local audio file by invoking whisper with the file path and a chosen 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 locally without an API key?

Local transcription without an API key is achieved by using Whisper CLI to process speech to text directly on your device. It operates entirely offline, bypassing the need for external cloud services or authentication.

How does local speech-to-text work for privacy-sensitive workflows?

Local speech-to-text works by running Whisper's CLI on-device, ensuring audio data never leaves your system. This privacy-aware mechanism processes meetings, lectures, or podcasts entirely offline without uploading files to external servers.

Do I need to install the Whisper binary to transcribe audio files?

Yes, you need the Whisper binary installed and accessible on your system to transcribe audio files. The CLI requires this local binary to execute speech-to-text conversion and generate text output without cloud processing.

Can I use different Whisper models to balance transcription accuracy and speed?

Yes, you can use multiple Whisper models to balance transcription accuracy and speed. The CLI supports varied model sizes and output formats, allowing you to choose the optimal configuration for transcribing podcasts, meetings, or video content.

What are the limitations of offline transcription with Whisper CLI?

Offline transcription with Whisper CLI requires the whisper binary to be installed locally and depends entirely on your device's processing power. Transcription speed and accuracy are constrained by the chosen model size and available hardware resources.