openai-whisper

Transcribe local audio files into text using the Whisper CLI.

Updated Apr 3, 2026
One-click install
npx skills add https://github.com/BEIRUX/agent-skills --skill openai-whisper-beirux
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/BEIRUX/agent-skills/tree/main/openai-whisper
Command: npx skills add https://github.com/BEIRUX/agent-skills --skill openai-whisper-beirux

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes audio locally using the Whisper CLI without needing an API key, enabling private and offline speech-to-text.

Core Features & Use Cases

  • Offline transcription: transcribe audio without internet, preserving privacy.
  • Model selection and translation: choose models (e.g., small, medium, large) and translate audio to subtitles.
  • Output formats and directories: generate transcript or subtitles in various formats and save to a chosen folder.
  • Use Case: Podcast transcription, meeting notes, and video captioning workflows.

Quick Start

Transcribe a local audio file using Whisper by specifying a model and output format.

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 offline without an API key?

You can transcribe audio offline by running the Whisper CLI locally on individual files or small batches. This approach requires no internet connection or external API keys, preserving privacy while generating text transcripts.

Can I use local speech-to-text for meeting notes and podcast transcription?

Local speech-to-text via the Whisper CLI supports podcast, lecture, and meeting-note workflows. It processes audio files locally to generate transcripts or subtitles directly on your machine without sending data externally.

Does offline transcription support multiple Whisper models for different accuracy levels?

Offline transcription supports multiple Whisper models including small, medium, and large options. You can select the appropriate model based on your hardware capabilities and desired accuracy for transcribing audio locally.

How do I translate audio to subtitles and save them in specific output formats?

You can translate audio to subtitles using the Whisper CLI with configurable output formats. Transcripts and subtitles are saved to a chosen directory, supporting various format options with local caching for efficient file management.

What is the best way to transcribe audio locally while keeping data private?

Local transcription using the Whisper CLI is the best way to keep audio data private. It processes files entirely offline without external API calls, ensuring sensitive meeting or lecture content never leaves your machine.

Do I need an internet connection to transcribe audio with the Whisper CLI?

No internet connection is needed to transcribe audio with the Whisper CLI. Once configured, it performs offline transcription locally without external API keys, making it suitable for private environments and secure workflows.