openai-whisper

Name: openai-whisper
Availability: InStock
Author: johnnywhitemike

Transcribe spoken audio into text using the local Whisper CLI.

Updated Apr 8, 2026

Search Tags:#captions #transcription #whisper #speech-to-text #local processing #audio files

Ready to run

npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill openai-whisper-johnnywhitemike

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts spoken audio into written text without needing any external speech-to-text API keys.

Core Features & Use Cases

Local transcription: Use the Whisper CLI to transcribe audio files on your machine.
Multiple output formats & translation: Produce captions or translated transcripts for downstream editing or sharing.
Model-driven quality: Choose smaller models for speed or larger models for higher accuracy.

Use Case: You have recorded meetings as audio files and want searchable transcripts for notes, minutes, or later review.

Quick Start

Run whisper /path/audio.mp3 --model medium --output_format txt --output_dir . to generate a local text 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 files locally without using an external speech-to-text API?▼

You can transcribe audio files locally by running the Whisper CLI on your machine, which converts spoken audio into searchable text transcripts without requiring external API keys.

What's the best way to generate captions or text transcripts from recorded meetings?▼

Generating captions from recorded meetings is done by passing your audio files to the Whisper CLI, which produces timed outputs and searchable text transcripts for later review.

Do I need an API key to convert speech to text using Whisper?▼

No, you do not need an API key to convert speech to text. The transcription is processed entirely locally using the Whisper binary installed on your machine.

How do I choose the right Whisper model for local transcription speed and accuracy?▼

Choosing the right Whisper model involves selecting smaller models for faster local transcription speed or larger models to achieve higher accuracy for your audio files.

Can I translate audio recordings into written text using the Whisper CLI?▼

Yes, you can translate audio recordings into written text using the Whisper CLI, which produces translated transcripts and timed outputs for downstream editing or sharing.

Where are Whisper models stored when I run local speech-to-text transcription?▼

Whisper models are downloaded to the user cache on your local machine during the first run, storing the necessary data for processing speech-to-text transcription.