openai-whisper

Transcribe audio and video files into text or SRT subtitles locally with Whisper CLI.

117|8|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/geezerrrr/motive --skill openai-whisper-geezerrrr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/geezerrrr/motive/tree/main/Motive/Resources/Skills.bundle/openai-whisper
Command: npx skills add https://github.com/geezerrrr/motive --skill openai-whisper-geezerrrr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes audio locally by leveraging the Whisper CLI, enabling offline speech-to-text without relying on external APIs.

Core Features & Use Cases

  • Local transcription: run whisper on audio files to produce text or subtitles without network access.
  • Model flexibility: choose different Whisper models to balance speed and accuracy.
  • Output options: generate plain text transcripts or SRT subtitles for video workflows.
  • Use Case: convert meeting recordings to searchable text for minutes and notes.

Quick Start

Run whisper on your audio file to generate a transcript or SRT subtitles locally.

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 internet connection?

Local transcription processes audio files into text entirely offline using the Whisper CLI. It runs without network access, caching models locally in ~/.cache/whisper to ensure data privacy and continuous availability.

Can I generate SRT subtitles for video files using offline transcription?

Offline transcription supports generating SRT subtitles alongside plain text transcripts. The Whisper CLI processes audio tracks from video files to produce timestamped subtitle outputs suitable for video editing workflows.

How do I balance transcription speed and accuracy when using Whisper?

Balancing transcription speed and accuracy is achieved by choosing different Whisper models during processing. The Whisper CLI allows model selection, letting you trade processing speed for transcription precision based on your hardware and needs.

Does local speech-to-text require any external APIs or cloud services?

Local speech-to-text does not require external APIs or cloud services. The Whisper CLI operates completely offline, performing all speech recognition locally on your machine without transmitting audio data to external servers.

What is the best way to convert meeting recordings to searchable text?

Converting meeting recordings to searchable text is done by running the Whisper CLI locally on your audio files. This offline transcription process generates plain text outputs, making meeting content easily searchable for minutes and notes.