openai-whisper

Transcribe audio files locally to text and subtitles using Whisper CLI.

Updated Feb 10, 2026
One-click install
npx skills add https://github.com/cogpy/clawcog --skill openai-whisper-cogpy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/cogpy/clawcog/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/cogpy/clawcog --skill openai-whisper-cogpy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables local speech-to-text transcription of audio files without requiring an API key, offering a private and cost-effective solution.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • Multiple Output Formats: Supports various output formats like plain text (txt) and subtitles (srt).
  • Use Case: Transcribe a meeting recording to generate a text transcript 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 text.

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?

To transcribe audio files locally without an API key, you can use this Skill to run speech-to-text transcription directly on your machine via the Whisper CLI. It provides a private and cost-effective solution for generating text transcripts.

Can I generate SRT subtitle files from an audio recording?

Yes, you can generate SRT subtitle files from an audio recording because this local speech-to-text transcription supports multiple output formats, including plain text (txt) and subtitles (srt).

Do I need the Whisper CLI installed to perform local speech-to-text transcription?

Yes, you need the Whisper CLI installed and configured on your local system to perform local speech-to-text transcription. This Skill acts as an interface to execute the transcription processing logic on your machine.

What is the best way to transcribe a meeting recording for easy searching?

The best way to transcribe a meeting recording for easy searching is using local speech-to-text transcription to generate a plain text transcript. This Skill processes the audio file locally to deliver searchable text output.

Does local speech-to-text transcription work with various audio formats?

Yes, local speech-to-text transcription works with various audio formats. The Skill leverages the Whisper CLI to process different types of audio files and output the transcription results in your chosen format.