openai-whisper

Transcribe audio files into text locally using the Whisper CLI.

1|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/bobvarkey/openclaw-workspace --skill openai-whisper-bobvarkey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/bobvarkey/openclaw-workspace/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/bobvarkey/openclaw-workspace --skill openai-whisper-bobvarkey

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper.

What problem does it solve?

This Skill removes the need for manual transcription by converting spoken audio into text locally with Whisper, without relying on an external API key.

Core Features & Use Cases

  • Local Speech-to-Text: Transcribe audio files on your machine using the Whisper CLI.
  • Translation Mode: Convert spoken audio into another language transcript when needed.
  • Format Output: Generate plain text or subtitle files for meetings, interviews, and recordings.

Quick Start

Ask to transcribe the attached audio file to text with Whisper using the medium model and save the result in the current folder.

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 files locally without an API key?

Local speech-to-text transcription with Whisper processes audio files directly on your machine, eliminating the need for an external API key. It converts meetings, interviews, and lectures into text without sending audio to an external service.

Can I generate subtitle files from audio recordings?

Generating subtitle files from audio recordings is supported by the Whisper transcription CLI. You can output plain text or subtitle formats for meetings and lectures, ensuring the transcribed content is ready for video integration.

Do I need the whisper binary installed to transcribe audio?

Yes, you need the whisper binary installed to transcribe audio with this local speech-to-text approach. The process also requires local model downloads to operate without relying on an external API key.

Does local transcription support translation of spoken audio?

Local transcription supports translation of spoken audio through the Whisper CLI. It can convert your recorded meetings or interviews into another language transcript directly on your machine without external services.

What is the best way to transcribe meetings locally without external services?

The best way to transcribe meetings locally without external services is using the Whisper CLI for speech-to-text conversion. It processes recordings directly on your machine, requiring only local model downloads to output text or subtitle files.