openai-whisper

Transcribe local audio files to text using the Whisper CLI.

386k|81.1k|Updated Nov 24, 2025
One-click install
npx skills add https://github.com/openclaw/openclaw --skill openai-whisper-openclaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/openclaw/openclaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/openclaw/openclaw --skill openai-whisper-openclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a local, privacy-preserving solution for converting spoken audio into written text, eliminating the need for cloud-based services and API keys.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • Multiple Formats: Supports various output formats for transcribed text.
  • Model Selection: Allows choosing different Whisper models for a balance of speed and accuracy.
  • Use Case: You need to transcribe a meeting recording stored on your computer without sending sensitive audio data to an external server.

Quick Start

Use whisper to transcribe the audio file located at /path/to/meeting.mp3 using the medium model and output the text to the current directory.

Frequently Asked Questions about openai-whisper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe an audio file locally without sending data to the cloud?

Local speech-to-text transcription converts spoken audio into written text directly on your machine. This Skill uses the Whisper CLI to process audio files locally, eliminating the need for cloud-based services or external API keys.

Do I need to install the Whisper binary before using this Skill for transcription?

Yes, you need the Whisper binary installed and configured for local model execution. This prerequisite allows the Skill to perform local speech-to-text transcription of voice notes and meeting recordings without relying on external servers.

What's the best way to transcribe a meeting recording stored on my computer?

To transcribe a meeting recording, use the Whisper CLI to process the audio file at a specified path. You can select a model like the medium model to balance speed and accuracy, outputting the transcribed text directly to your chosen directory.

Can I choose between different models for speech-to-text transcription?

Yes, local speech-to-text transcription allows choosing different Whisper models. This feature enables you to select a specific model to achieve the desired balance between transcription speed and text accuracy for your audio files.

Does local transcription support multiple output formats for the transcribed text?

Yes, local speech-to-text transcription supports various output formats for the transcribed text. This allows you to convert audio content into written documentation or analysis formats that best suit your workflow requirements.