openai-whisper

Transcribe audio to text locally using the Whisper CLI.

55|12|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/Yapie0/safe-openclaw --skill openai-whisper-yapie0
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Yapie0/safe-openclaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/Yapie0/safe-openclaw --skill openai-whisper-yapie0

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local transcription of audio using Whisper CLI without needing API keys.

Core Features & Use Cases

  • Offline transcription: transcribe audio locally with Whisper CLI.
  • Language translation: optionally translate audio by using --task translate.
  • Quick experimentation: select different models and settings for on-device processing.

Quick Start

Run whisper on your audio file to transcribe it locally and save the output.

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?

You can transcribe audio to text locally without an API key by running the Whisper CLI binary directly on your audio files. The tool processes various audio formats entirely offline on your device, requiring no external API authentication.

Can I translate speech to text offline using Whisper CLI?

Yes, you can translate speech to text offline using Whisper CLI. By applying the --task translate command, the tool translates spoken audio into text locally on your device without requiring an internet connection or API key.

Do I need to install the Whisper binary to use local speech-to-text transcription?

Yes, local speech-to-text transcription requires the Whisper binary to be installed and accessible in your system PATH. Model caches and downloads are automatically stored under your user home directory during the processing of audio files.

What is the best way to generate offline subtitles and meeting notes from audio?

The best way to generate offline subtitles and meeting notes is by using the Whisper CLI for local transcription. It supports selecting different model sizes, from small to large, to balance processing speed and accuracy for your archival indexing tasks.

Does local audio transcription support multiple languages and audio formats?

Yes, local audio transcription supports multiple languages and various audio formats. The Whisper CLI processes diverse audio inputs entirely offline, allowing you to select appropriate models to handle different languages and optional speech translation tasks effectively.