openai-whisper

Transcribe and translate audio files locally using the Whisper CLI.

3|1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/SeanHogg/coderClaw --skill openai-whisper-seanhogg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/SeanHogg/coderClaw/tree/main/product/skills/openai-whisper
Command: npx skills add https://github.com/SeanHogg/coderClaw --skill openai-whisper-seanhogg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables local speech-to-text transcription of audio files without requiring an API key, ensuring privacy and offline functionality.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • Translation: Translate audio from various languages into English.
  • Multiple Output Formats: Supports various output formats like TXT and SRT.
  • Use Case: Transcribe a meeting recording into a text document for easy searching and summarization.

Quick Start

Use whisper to transcribe the audio file located at /path/to/audio.mp3 using the medium model and output the result as a text file.

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 files locally without an API key?

Local speech-to-text transcription can be performed directly on your machine using the Whisper CLI, eliminating the need for an API key. This approach ensures privacy and enables offline functionality for processing audio files.

Can I translate spoken audio from another language into English offline?

Yes, audio translation into English can be executed locally using the Whisper CLI. This functionality allows you to translate spoken content from various languages directly on your machine without requiring external API calls.

Do I need to install the Whisper CLI binary to transcribe meeting recordings?

Yes, the Whisper CLI binary must be installed and accessible in your system's PATH to transcribe meeting recordings. This local setup serves as the foundational requirement for executing the speech-to-text process.

What audio transcription output formats are supported for voice notes?

The transcription process supports multiple output formats, including TXT and SRT. This allows you to transcribe voice notes into a text document for easy searching and summarization, depending on your required format.

How do I start local transcription using a specific Whisper model?

To start local transcription, you use the Whisper CLI to specify the audio file path, select a model like medium, and define the output format. This executes the speech-to-text task directly on your local machine.

What are the limitations of local audio transcription with Whisper?

Local audio transcription relies entirely on your machine's processing capabilities and requires the Whisper CLI binary in the system PATH. It is best suited for transcribing voice notes, lectures, and meetings where offline privacy is prioritized.