openai-whisper

Transcribe audio files locally using the Whisper CLI.

1|Updated Apr 10, 2026
One-click install
npx skills add https://github.com/pertain99/openclaw-better --skill openai-whisper-pertain99
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/pertain99/openclaw-better/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/pertain99/openclaw-better --skill openai-whisper-pertain99

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio locally into text without relying on external services.

Core Features & Use Cases

  • Offline transcription: Transcribe audio files locally using the Whisper CLI without sending data to external APIs.
  • Multi-language support: Handle a variety of languages and, if needed, translate output with the appropriate CLI task.
  • Real-world scenario: Imagine recording a podcast and needing a quick transcript without uploading files to cloud services for privacy and speed.

Quick Start

Run whisper /path/audio.mp3 --model medium --output_format txt to generate a local transcription.

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 offline without using an external API?

You can transcribe audio offline by using the Whisper CLI to process local audio files into text without sending data to external services. This requires having the Whisper CLI installed and models cached locally on your machine.

What is local speech-to-text transcription and how does it handle privacy?

Local speech-to-text transcription processes audio files entirely on your machine using the Whisper CLI, ensuring data privacy. It converts spoken audio into text without uploading files to cloud APIs, keeping sensitive recordings secure and isolated.

Can I translate audio to English text using the Whisper CLI?

Yes, you can translate audio using the Whisper CLI by specifying the translation task. The CLI supports multi-language audio input and can generate translated text output alongside standard transcription workflows.

Do I need an API key to transcribe audio files with Whisper?

No, you do not need an API key to transcribe audio files. Local transcription with the Whisper CLI operates entirely offline without relying on external services, requiring only the CLI tool installed and models cached locally.

What is the best way to generate a text transcript from a local audio file?

The best way to generate a local text transcript is using the Whisper CLI with the command `whisper /path/audio.mp3 --model medium --output_format txt`, which processes the audio offline and outputs a text file.

What are the requirements for running offline transcription with Whisper?

Offline transcription with Whisper requires the Whisper CLI to be installed locally and the necessary models to be cached on your machine. It supports standard transcription and translation tasks via the CLI without external dependencies.