openai-whisper

Transcribe local audio files to text using the Whisper CLI.

Updated Dec 6, 2016
One-click install
npx skills add https://github.com/majunbao/learn --skill openai-whisper-majunbao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/majunbao/learn/tree/main/openclaw_tags/openclaw-2026.3.2/skills/openai-whisper
Command: npx skills add https://github.com/majunbao/learn --skill openai-whisper-majunbao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local, offline transcription of speech without needing an API key or online services, preserving privacy.

Core Features & Use Cases

  • Privacy-preserving transcription on-device without internet.
  • Supports Whisper models and outputs in TXT, SRT, or VTT formats for offline pipelines.
  • Use cases include transcribing interviews, lectures, and meetings while keeping data on-device.

Quick Start

Transcribe a local audio file using whisper, for example whisper /path/audio.mp3 --model medium --output_format txt.

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 to text locally without an internet connection?

You can transcribe audio locally by running the Whisper CLI command, such as whisper /path/audio.mp3, to process speech into text directly on your device without internet access.

What audio transcription output formats are supported by the Whisper CLI?

The Whisper CLI supports TXT, SRT, and VTT transcription output formats. You can specify your desired format using the --output_format flag to integrate transcribed speech into offline pipelines.

Do I need an API key to run speech-to-text transcription on-device?

No, an API key is not required for on-device speech-to-text. Whisper performs local transcription offline, allowing you to process audio privately without needing API keys or external online services.

Can I batch process media files for offline transcription in privacy-sensitive environments?

Yes, Whisper supports batch processing of media files for offline transcription in privacy-sensitive environments. All data remains on-device, making it ideal for transcribing interviews, lectures, and meetings securely.

How do I select a specific transcription model when converting speech to text?

To select a specific transcription model when converting speech to text, use the --model flag in your Whisper CLI command, such as specifying --model medium to balance accuracy and processing speed.

What is the best way to transcribe meetings while keeping data on-device?

The best way to transcribe meetings while keeping data on-device is using local Whisper speech-to-text. It processes audio files offline, ensuring privacy without sending your recorded meeting data to external API servers.