openai-whisper

Transcribe audio files to text locally using the Whisper CLI.

Updated Jan 16, 2026
One-click install
npx skills add https://github.com/czue/clawdbot --skill openai-whisper-czue
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/czue/clawdbot/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/czue/clawdbot --skill openai-whisper-czue

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local speech-to-text processing without relying on external APIs, preserving privacy and enabling offline transcription.

Core Features & Use Cases

  • Offline transcription using the Whisper CLI directly on your device.
  • Supports multiple models and languages for on-device transcription across meetings, interviews, podcasts, and voice notes.
  • Use case: privately transcribe conversations or media without sending data to cloud services.

Quick Start

Install Whisper and run a transcription on your audio file 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 sending data to external APIs?

Local transcription without external APIs is achieved by running the Whisper CLI directly on your device. This offline speech-to-text approach processes meetings, interviews, and podcasts privately on your workstation without sending audio data to cloud services.

Do I need an API key to run offline speech-to-text transcription?

No API key is required for offline speech-to-text transcription using the Whisper CLI. The tool operates offline with local models on your personal device, completely removing the need for external API authentication or cloud service credentials.

Can I use Whisper CLI for private transcription of meetings and podcasts?

Yes, Whisper CLI supports private transcription of meetings and podcasts by running on-device. It handles multiple languages and models locally, allowing you to generate text transcripts without uploading your audio files to cloud services.

What is the best way to set up local speech-to-text on a developer workstation?

Setting up local speech-to-text involves installing the Whisper binary on your developer workstation, for example via Homebrew. Once the CLI is installed, you can execute offline transcriptions on audio files to generate text transcripts.

Does offline transcription with Whisper CLI require an internet connection?

Offline transcription with the Whisper CLI does not require an internet connection. After installing the binary, the tool operates completely offline using local models, ensuring audio files are processed privately on your device without network access.