openai-whisper

Transcribe audio to text locally using the Whisper CLI.

Updated Mar 19, 2026

Search Tags:#cli #offline #transcription #whisper #audio #local #speech-to-text

Ready to run

npx skills add https://github.com/jason9693/Open-Jordy --skill openai-whisper-jason9693

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/jason9693/Open-Jordy/tree/main/openjordy/skills/openai-whisper
Command: npx skills add https://github.com/jason9693/Open-Jordy --skill openai-whisper-jason9693

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes audio locally using the Whisper CLI to convert speech to text without requiring an API key.

Core Features & Use Cases

Local transcription with no API key required.
Supports model selection and translation/transcription tasks on your own machine.
Useful for privacy-preserving transcripts, accessibility tooling, and offline workflows.

Quick Start

Run Whisper on your audio file using the desired model to generate 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?▼

Local audio transcription without an API key is achieved by running the Whisper CLI on your machine to convert speech to text directly. This Skill uses the Whisper CLI for on-device processing, ensuring privacy and eliminating external API dependencies.

Can I use Whisper for offline speech-to-text transcription?▼

Yes, offline speech-to-text transcription is supported by running the Whisper CLI locally. This Skill processes audio files on your own machine without requiring internet connectivity or an external API key, making it suitable for privacy-preserving workflows.

Do I need the Whisper CLI installed to use local transcription?▼

Yes, you must have the Whisper CLI installed on your machine to use this local transcription Skill. It acts as the core engine for converting speech to text on-device, supporting model selection and output formatting during processing.

What is the best way to transcribe audio privately on my own machine?▼

The best way to transcribe audio privately is by using the Whisper CLI for local on-device processing. This approach prevents data from leaving your machine, requires no API key, and supports model selection for customized speech-to-text conversion.

Does local audio transcription support translation and model selection?▼

Local audio transcription supports both translation and transcription tasks using the Whisper CLI. You can select desired models and configure output formatting directly on your machine to process audio files according to your specific needs.