openai-whisper

Transcribe audio locally using the Whisper CLI without API keys.

5|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/p-sree-sai-pavan/P.A.R.K.E.R --skill openai-whisper-p-sree-sai-pavan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/p-sree-sai-pavan/P.A.R.K.E.R/tree/main/gateway/skills/openai-whisper
Command: npx skills add https://github.com/p-sree-sai-pavan/P.A.R.K.E.R --skill openai-whisper-p-sree-sai-pavan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Whisper provides local speech-to-text transcription using the Whisper CLI, eliminating dependence on external APIs and key management. This tool helps users convert audio recordings into accurate transcripts on their own machines.

Core Features & Use Cases

  • Local, offline transcription using the Whisper CLI
  • Supports model selection (e.g., small, medium, large) and output formats
  • Translation capability when using translate task for multilingual audio

Quick Start

Run whisper on an audio file to generate a transcript 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 using cloud APIs?

Local transcription without cloud APIs is achieved by running the Whisper CLI on your machine. This eliminates external API dependence and key management while converting audio recordings into text.

Do I need an API key to run speech-to-text conversion with Whisper?

No API key is needed to run speech-to-text conversion with Whisper. The tool operates entirely offline using the local Whisper binary, requiring no cloud services or external authentication for transcription.

Can I translate multilingual audio to text offline using Whisper?

Yes, you can translate multilingual audio to text offline using Whisper. By selecting the translate task, the CLI converts spoken audio from various languages into English text locally.

What prerequisites are needed to start local transcription with the Whisper CLI?

The prerequisite for local transcription with the Whisper CLI is having the Whisper binary installed on your system, such as via Brew. Once installed, you can run it on audio files to generate transcripts.

How do I select different Whisper models and output formats for audio processing?

Selecting different Whisper models and output formats for audio processing is supported through the CLI. You can choose model sizes like small, medium, or large to balance speed and accuracy during transcription.