openai-whisper

Transcribe audio locally to text using the Whisper CLI.

2.5k|423|Updated Mar 28, 2026

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

Ready to run

npx skills add https://github.com/Bitterbot-AI/bitterbot-desktop --skill openai-whisper-bitterbot-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/Bitterbot-AI/bitterbot-desktop --skill openai-whisper-bitterbot-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio locally to text using the Whisper CLI, enabling privacy-respecting, offline transcription without API keys.

Core Features & Use Cases

Local transcription with the Whisper CLI for offline, on-device processing.
Supports transcription and translation tasks via CLI options; suitable for podcasts, lectures, or meetings.
Provides guidance to install and run Whisper locally.

Quick Start

Run whisper on your audio file to produce a local transcription.

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?▼

Transcribe audio locally without an API key by running the Whisper CLI on your developer workstation. This offline speech-to-text process ensures privacy and requires the Whisper binary and model files to be installed.

Can I use Whisper for offline transcription of podcasts and meetings?▼

Yes, Whisper supports offline transcription for podcasts, lectures, and meetings. By executing the local Whisper CLI on your audio files, you generate text transcripts securely on your own machine.

Does local speech-to-text with the Whisper CLI require model files?▼

Yes, local speech-to-text with the Whisper CLI requires installing both the Whisper binary and model files. Users can select specific models via CLI options to balance transcription accuracy and system resources.

How do I translate audio to text using Whisper command-line options?▼

Translate audio to text using the Whisper CLI by specifying translation tasks through command-line options. This local processing converts spoken audio into translated text without needing an external API.

What is the best way to run speech-to-text on a developer workstation?▼

The best way to run speech-to-text on a developer workstation is using the local Whisper CLI. It provides on-device transcription and translation, requiring only the binary, model files, and CLI options for execution.