openai-whisper

Transcribe local audio files to text using OpenAI Whisper CLI.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/dioerden/OpenClaw-Flash-Vault --skill openai-whisper-dioerden
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/dioerden/OpenClaw-Flash-Vault/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/dioerden/OpenClaw-Flash-Vault --skill openai-whisper-dioerden

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai-whisper, and includes scripts (resource) components.

What problem does it solve?

This Skill solves the issue of converting spoken audio to text efficiently and without the need for an API key, offering a local solution for speech transcription.

Core Features & Use Cases

  • Local Speech-to-Text: Transcribe audio directly from local files, providing instant results.
  • Whisper CLI Integration: Utilizes the OpenAI Whisper CLI to handle audio conversion to text.
  • No API Key Required: Allows transcription without relying on third-party API services.
  • Use Case: Ideal for individuals who need to transcribe lectures, interviews, or personal recordings on their devices.

Quick Start

To transcribe the file 'lecture.mp3' to text, run:

whisper lecture.mp3 --output_format txt --output_dir transcriptions

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 an API key?

To transcribe audio to text locally without an API key, you can use the OpenAI Whisper CLI to process audio files directly on your device. This method provides instant speech-to-text conversion without relying on third-party services.

Can I use Whisper CLI for speech-to-text on my personal recordings?

Yes, you can use Whisper CLI for speech-to-text on personal recordings. It is specifically ideal for individuals needing to transcribe lectures, interviews, or personal audio files on their local file systems.

How do I convert an MP3 file to text using Whisper?

To convert an MP3 file to text using Whisper, run the command 'whisper lecture.mp3 --output_format txt --output_dir transcriptions' in your terminal. This executes local speech-to-text conversion and outputs the result as a text file.

Does local audio transcription require third-party API services?

Local audio transcription does not require third-party API services or an API key. By utilizing the OpenAI Whisper CLI and Python, the speech-to-text process executes entirely on your local file system.

Is Python required to run local speech-to-text conversions with Whisper?

Python is required to run local speech-to-text conversions with Whisper. The Skill utilizes OpenAI Whisper and Python to execute the CLI-based audio transcription directly on local file systems.

What is the best way to transcribe interviews without paying for API services?

The best way to transcribe interviews without paying for API services is using a local speech-to-text solution like OpenAI Whisper CLI. It handles audio conversion to text directly on your device without any API key dependency.