openai-whisper

Transcribe local audio files to text or SRT using the Whisper CLI.

4|2|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Clawdi-AI/openclaw --skill openai-whisper-clawdi-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Clawdi-AI/openclaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/Clawdi-AI/openclaw --skill openai-whisper-clawdi-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a local, privacy-focused solution for transcribing audio files without relying on external APIs or requiring an API key.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • Multiple Formats: Supports various audio input formats and can output transcriptions in text or SRT format.
  • Use Case: You need to transcribe a lengthy meeting recording for documentation but want to ensure the audio data stays on your local system for privacy.

Quick Start

Use whisper to transcribe the audio file located at /path/to/audio.mp3 using the medium model and output the result as a text file.

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 locally without an API key?

To transcribe audio locally without an API key, you can use the Whisper CLI to perform speech-to-text directly on your machine. This processes voice notes and meeting recordings entirely on your system, ensuring audio data privacy.

What audio formats can I transcribe using local speech-to-text?

Local speech-to-text using the Whisper CLI supports various audio input formats for transcription. You can process your voice notes or meeting recordings and output the resulting transcriptions in either standard text or SRT format.

Do I need to install anything to transcribe audio files locally?

Yes, to transcribe audio files locally you need the 'whisper' binary installed and accessible in your system's PATH. This local speech-to-text execution relies entirely on the Whisper CLI without requiring external APIs.

Can I transcribe a meeting recording and output it as an SRT file?

Yes, you can transcribe a meeting recording and output it as an SRT file. The local speech-to-text process through the Whisper CLI supports generating transcriptions in both text and SRT formats for documentation.

Is local transcription suitable for ensuring video audio remains private?

Local transcription is highly suitable for keeping video audio private. By using the Whisper CLI directly on your machine, the speech-to-text processing bypasses external APIs, ensuring your audio data never leaves your local system.