openai-whisper

Transcribe spoken audio locally using the Whisper CLI without an API key.

7|12|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/borealBytes/my-farm-advisor --skill openai-whisper-borealbytes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/borealBytes/my-farm-advisor/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/borealBytes/my-farm-advisor --skill openai-whisper-borealbytes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe spoken audio locally using the Whisper CLI without requiring an API key, preserving privacy and avoiding network latency.

Core Features & Use Cases

  • Local transcription: convert audio to text without sending data to external services.
  • Flexible workflows: supports different Whisper models and output formats for transcripts or subtitles.
  • Easy integration: CLI-based workflow that fits into scripts and automation pipelines.

Quick Start

Transcribe an audio file by running whisper with your chosen model to produce a transcript.

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 API key?

To transcribe audio locally without an API key, use the Whisper CLI which processes spoken audio directly on your machine, ensuring privacy and avoiding network latency.

Do I need a Whisper CLI installation to transcribe podcasts offline?

Yes, offline transcription for podcasts relies on a local Whisper CLI installation and default model behavior, including caching downloaded models to ~/.cache/whisper.

What is the best way to generate subtitles for media without sending data to external services?

Local transcription with Whisper CLI is the best way to generate subtitles without external services, supporting different output formats for transcripts or subtitles.

Can I use the Whisper CLI for ad hoc meeting transcriptions?

Yes, the Whisper CLI is applicable for ad hoc transcriptions, podcasts, meetings, and media captioning, offering optional translation or transcription modes.

How does local speech-to-text fit into automation pipelines?

Local speech-to-text fits into automation pipelines through an easy-integration CLI-based workflow, allowing scripts to automatically convert audio to text.