openai-whisper

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

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/StanH123h/clawdbot-self-use --skill openai-whisper-stanh123h
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/StanH123h/clawdbot-self-use/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/StanH123h/clawdbot-self-use --skill openai-whisper-stanh123h

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a local, privacy-focused solution for transcribing audio files into text without relying on external APIs or sending data to the cloud.

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 or SRT subtitle format.
  • Use Case: You need to transcribe a meeting recording stored on your local drive for documentation purposes, ensuring all audio data remains private.

Quick Start

Use whisper to transcribe the audio file located at /path/to/meeting.mp3 using the medium model and output the transcription 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 sending data to the cloud?

Local speech-to-text transcription can be performed directly on your machine using the OpenAI Whisper CLI. It processes audio files offline, ensuring all your spoken audio data remains completely private on your local drive.

What audio formats are supported for offline speech-to-text transcription?

Offline speech-to-text transcription supports various audio input formats for processing. The transcription output can be generated as either a plain text file or an SRT subtitle format, depending on your documentation or subtitle requirements.

Do I need the Whisper binary installed in my system PATH to transcribe audio?

Yes, local transcription requires the Whisper binary to be installed and accessible in your system's PATH. This local installation is what enables the offline audio processing and translation tasks without relying on external APIs.

Can I generate SRT subtitles from a local meeting recording?

Yes, you can transcribe a local meeting recording into SRT subtitle format using the Whisper CLI. By specifying the audio file path and desired model, the transcription process outputs timestamped subtitles suitable for video documentation.

What is the best way to ensure privacy when converting speech to text?

The best way to ensure privacy during speech-to-text conversion is to use local offline transcription. By processing audio files entirely on your own machine with the Whisper CLI, you prevent sensitive meeting or voice data from being sent to external cloud APIs.

How do I transcribe an mp3 file using a specific Whisper model locally?

To transcribe an mp3 file locally, use the Whisper CLI and specify the audio file path along with your desired model, such as the medium model. The CLI processes the audio offline and outputs the resulting transcription as a text file.