openai-whisper

Transcribe audio files to text locally using the Whisper CLI.

2|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/papachong/RHClaw --skill openai-whisper-papachong
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/papachong/RHClaw/tree/main/RHClaw-Desktop/src-tauri/skills/openai-whisper
Command: npx skills add https://github.com/papachong/RHClaw --skill openai-whisper-papachong

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a simple way to transcribe audio locally using the Whisper CLI, avoiding external API usage and keeping sensitive audio data on your machine.

Core Features & Use Cases

  • Local CLI transcription: Use the whisper command-line tool to convert audio into text without sending data to external services.
  • Model selection and translation: Choose smaller models for speed or larger models for accuracy, and optionally perform speech translation into subtitles.
  • Local caching and output formats: Models are downloaded to the local cache and outputs can be produced as plain text or subtitle files for downstream editing and indexing.
  • Use Case: Convert meeting recordings, interviews, or podcast episodes into searchable transcripts and SRT subtitle files on a laptop without an API key.

Quick Start

Transcribe the audio file meeting.mp3 locally into plain text using the whisper CLI with the medium model and save the output to the current directory.

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 using an external API?

Local speech-to-text transcription without an external API is achieved by using the Whisper CLI to convert audio files into text directly on your machine. This approach processes meeting recordings and podcasts entirely offline, keeping sensitive data secure.

Can I generate SRT subtitle files from audio recordings offline?

Yes, you can generate SRT subtitle files offline using the local Whisper CLI. The tool supports multiple output formats including plain text and SRT, allowing you to produce subtitle files for downstream editing and indexing from audio recordings.

Do I need an API key to convert meeting recordings to text on my laptop?

No, you do not need an API key to convert meeting recordings to text. The local Whisper CLI operates entirely offline on your laptop, avoiding external API usage and keeping sensitive audio data on your local machine without requiring authentication.

How do I choose the right Whisper model size for offline transcription?

Choose smaller Whisper models for faster offline transcription speed or larger models for higher text accuracy. The Whisper CLI supports multiple model sizes, and selected models are downloaded to your local cache for reuse during subsequent speech-to-text processing.

What are the limitations of local offline speech-to-text with Whisper?

Local offline speech-to-text with Whisper requires the whisper binary installed locally on your machine. Processing speed and transcription accuracy depend on your local hardware capabilities and the selected model size, which may limit real-time processing of large audio files.