openai-whisper

Transcribe audio into text and subtitle files using the local Whisper CLI.

5|Updated Jan 31, 2026

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

Ready to run

npx skills add https://github.com/kcns008/clusterclaw --skill openai-whisper-kcns008

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/kcns008/clusterclaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/kcns008/clusterclaw --skill openai-whisper-kcns008

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It turns spoken audio into accurate text without sending files to an external API, making transcription faster, private, and easy to automate.

Core Features & Use Cases

Local speech-to-text: Convert interviews, meetings, lectures, and voice notes into text on your own machine.
Translation support: Translate spoken language into another language while transcribing.
Flexible output: Generate plain text or subtitle files for editing, publishing, or archiving.

Quick Start

Use the Whisper CLI to transcribe your audio file locally and choose the output format you need.

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 to text locally without an API key?▼

You can transcribe audio to text locally without an API key by using the Whisper CLI. This skill processes audio files offline on your own machine, requiring only an installed whisper binary and downloaded models to generate accurate text outputs.

Can I translate spoken language while transcribing audio files?▼

Yes, you can translate spoken language while transcribing audio files. The local Whisper CLI supports speech-to-text translation workflows, allowing you to convert spoken audio into text in another language simultaneously during offline processing.

Do I need to install whisper and download models to use this transcription skill?▼

Yes, you need to install a whisper binary and download models to use this transcription skill. Because it processes audio locally without an API key, having the necessary models downloaded beforehand is required for offline speech-to-text execution.

What's the best way to generate subtitle files from interviews and meetings?▼

The best way to generate subtitle files from interviews and meetings is using the local Whisper CLI. It converts your audio recordings into flexible output formats, including subtitle files, enabling easy editing, publishing, or archiving directly on your machine.

Does offline speech-to-text work for processing podcasts and voice notes?▼

Yes, offline speech-to-text works for processing podcasts and voice notes. The local Whisper CLI transcribes these audio recordings into text without sending files to an external API, making the process faster, private, and easy to automate.

What are the limitations of transcribing audio without an external API?▼

A limitation of transcribing audio without an external API is the local processing requirement. You must have an installed whisper binary and sufficient storage for downloaded models on your machine to process audio files offline for speech-to-text tasks.