openai-whisper

Transcribe and translate audio files locally using the Whisper CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Nirpat3/MIB007 --skill openai-whisper-nirpat3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Nirpat3/MIB007/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/Nirpat3/MIB007 --skill openai-whisper-nirpat3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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

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.
  • Use Case: You have a recorded meeting in an MP3 format and need a text transcript for documentation. Use this Skill to convert the audio into a text file.

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 an audio file locally without using a cloud-based API?

Local speech-to-text transcription converts audio files into text using the Whisper CLI, bypassing cloud-based APIs. It offers a private, cost-effective method for transcribing recorded meetings and interviews.

What do I need to run local speech-to-text transcription?

Local speech-to-text transcription requires the whisper executable installed and accessible in your system's PATH. Once configured, you can process audio files directly without external dependencies.

Can I translate audio files from other languages into English locally?

Yes, local speech-to-text translation supports translating audio from various languages into English. The Whisper CLI processes multilingual audio files and outputs English text results.

How do I transcribe an MP3 file to text using the Whisper CLI?

To transcribe an MP3 file, invoke the whisper executable with the file path, specify the model, and output the result as a text file. This processes the audio entirely locally.

Is local transcription suitable for private and sensitive audio recordings?

Local transcription is highly suitable for sensitive audio recordings because it processes files directly on your machine without requiring an API key or sending data to external servers, ensuring complete privacy.

What are the limitations of local speech-to-text transcription?

The primary limitation of local speech-to-text transcription is the strict dependency on having the whisper executable pre-installed and accessible in the system PATH. Processing speed depends entirely on your local hardware resources.