One-click install
npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill openai-whisper-moodmnky-llc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/MOODMNKY-LLC/mnky-atlas/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill openai-whisper-moodmnky-llc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users who need to convert audio files (such as meeting recordings, interviews, or podcasts) to text without paying for cloud speech-to-text services or sharing sensitive audio data with third parties can use this skill to run transcription entirely on their local device at no cost.

Core Features & Use Cases

  • Local Private Transcription: Run speech-to-text entirely on your device, no audio data leaves your machine, no API keys required.
  • Multi-format & Task Support: Transcribe common audio formats like MP3, M4A, and WAV, with options for translating audio to English and exporting subtitles in SRT format.
  • Use Case: A researcher can transcribe hours of sensitive interview recordings locally to avoid sending participant data to external cloud services.

Quick Start

Use the openai-whisper skill to transcribe the audio file 'team-meeting-recording.mp3' to a plain text file saved in your current working 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 to text locally without sending files to the cloud?

To transcribe audio locally, you can use the Whisper CLI tool to run speech-to-text entirely on your device. This ensures no audio data leaves your machine and requires no API keys, keeping your files completely private.

Can I transcribe MP3 and M4A audio files for free using local speech-to-text?

Yes, you can transcribe common audio formats like MP3, M4A, and WAV for free. By running the open-source Whisper CLI locally, you avoid cloud service fees while processing meeting recordings, interviews, or podcasts directly on your hardware.

Do I need an internet connection or API keys to generate subtitles locally?

No API keys or internet connection are required for local transcription. You only need the open-source Whisper CLI tool installed on your machine to generate subtitle exports in SRT format or plain text transcripts from your audio files.

How do I balance transcription speed and accuracy when converting audio files?

You can balance transcription speed and accuracy by configuring the Whisper model sizes. Choosing smaller models speeds up the local transcription process, while larger models improve accuracy for complex audio files, meeting recordings, or podcasts.

What is the best way to translate sensitive interview recordings to English text?

The best way to translate sensitive interview recordings is using local audio translation with Whisper CLI. It supports multilingual translation to English, ensuring participant data remains private and avoiding external cloud speech-to-text services.