openai-whisper

Transcribe audio files locally using the OpenAI Whisper CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/robertwaltos/openclaw --skill openai-whisper-robertwaltos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/robertwaltos/openclaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/robertwaltos/openclaw --skill openai-whisper-robertwaltos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a local, privacy-focused solution for converting spoken audio into written text, eliminating the need for cloud-based APIs and associated costs or data concerns.

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 plain text (.txt) or subtitle formats (.srt).
  • Use Case: Quickly transcribe meeting recordings, voice notes, or interviews without uploading sensitive audio to external servers.

Quick Start

Use whisper to transcribe the audio file located at /path/to/your/audio.mp3 using the medium model and save the output 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 files locally without using cloud APIs?

Local speech-to-text transcription can be performed directly on your machine using the OpenAI Whisper CLI. This offline audio processing approach eliminates cloud API costs and prevents sensitive audio data from being uploaded to external servers.

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

Offline speech-to-text transcription supports various audio input formats for processing. The Whisper CLI can output the resulting transcriptions as plain text files or subtitle formats, making it suitable for meeting recordings, voice notes, and interviews.

Do I need to install the Whisper binary before using local audio transcription?

Yes, local audio transcription requires the Whisper binary to be installed and accessible in your system's PATH. This prerequisite allows the system to execute offline speech-to-text processing commands directly on your machine.

How do I transcribe an audio file using a specific Whisper model locally?

To transcribe audio locally, use the Whisper CLI to specify your audio file path and select a model, such as the medium model. The command processes the audio offline and saves the output as a text file.

What is the best way to generate subtitle files from voice recordings offline?

Generating subtitle files offline is achieved by running local speech-to-text transcription with the Whisper CLI. This method processes audio files directly on your machine and can output the results in subtitle formats for your recordings.