openai-whisper

Convert spoken audio to text locally using Whisper CLI without API keys.

1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/Arry8/openclaw-edge --skill openai-whisper-arry8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Arry8/openclaw-edge/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/Arry8/openclaw-edge --skill openai-whisper-arry8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribing audio locally without relying on external APIs is essential for privacy and offline workflows.

Core Features & Use Cases

  • Local transcription with Whisper CLI, no API key required.
  • Supports transcription and translation modes, model selection, and output formats.
  • Works on single files or batches, with model defaults and offline model caching.

Quick Start

Run whisper on your audio file with the desired model to generate a transcription locally.

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?

Transcribe audio to text locally without an API key by using the Whisper CLI to automatically convert spoken audio files into written text. This offline approach ensures privacy by processing single files or batches directly on your system.

Can I translate spoken audio to English text offline?

Yes, you can translate spoken audio to English text offline using the Whisper CLI's translation mode. It processes your local audio files securely without requiring external APIs or internet access.

Do I need the Whisper binary installed to transcribe audio locally?

Yes, you need the Whisper binary available on your system to transcribe audio locally. The Skill relies on this local installation to process audio files, select models, and generate text outputs without external API dependencies.

What is the best way to batch transcribe audio files for media subtitling?

The best way to batch transcribe audio files for media subtitling is using the Whisper CLI with its supported output formats. It handles multiple local files efficiently, offering model selection and offline caching for private, scalable workflows.

Does local transcription with Whisper support different model sizes?

Local transcription with Whisper supports model selection, allowing you to choose different model sizes for your audio processing. Models are cached locally for offline workflows, balancing transcription accuracy and system performance.