openai-whisper

Transcribe audio files to text locally using the Whisper CLI.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/Yogi-076/Vajrascan.on --skill openai-whisper-yogi-076
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Yogi-076/Vajrascan.on/tree/main/moltbot/skills/openai-whisper
Command: npx skills add https://github.com/Yogi-076/Vajrascan.on --skill openai-whisper-yogi-076

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a simple way to transcribe audio to text locally using the Whisper CLI so you can convert recordings without sending data to cloud services or providing API keys.

Core Features & Use Cases

  • Offline transcription: Run Whisper locally to transcribe meeting recordings, interviews, or voice notes while preserving privacy.
  • Model selection for speed vs accuracy: Choose smaller models for faster, low-resource transcriptions or larger models for higher accuracy.
  • Simple CLI workflow: Produce plain text, subtitles, or translated transcripts for integration into documentation and post-processing pipelines.

Quick Start

Transcribe meeting.mp3 to plain text using the medium model and save the result to the current directory.

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 to text locally without cloud API keys?

Transcribe audio files locally using the Whisper CLI to convert recordings to text without sending data to cloud services or providing API keys. It processes meeting recordings, interviews, and voice notes entirely offline.

Can I generate subtitles from audio recordings using offline speech-to-text?

Offline speech-to-text via the Whisper CLI produces plain text, subtitles, or translated transcripts. You can generate subtitle files from meeting recordings and voice notes for integration into documentation pipelines.

Do I need a specific environment to run offline transcription with Whisper?

Offline transcription requires a locally installed whisper binary and sufficient disk space for model downloads. You can optionally select smaller models for faster processing or larger models for higher accuracy.

What is the best way to balance speed and accuracy for local audio transcription?

Local audio transcription allows model selection to balance speed and accuracy. Choose smaller models for faster, low-resource transcriptions or larger models to achieve higher accuracy for complex speech-to-text tasks.

Why use local speech-to-text instead of cloud-based transcription services?

Local speech-to-text preserves privacy by running Whisper offline without sending data to cloud services. It eliminates the need for API keys while still handling offline transcription tasks like meeting recordings and voice notes.