whisper

Transcribe audio files into text in over 90 languages using the Whisper ASR model.

Updated Mar 23, 2026

Search Tags:#speech recognition #audio transcription #asr #speech to text #language processing

Ready to run

npx skills add https://github.com/chrishuffman5/skills --skill whisper-chrishuffman5

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/chrishuffman5/skills/tree/main/whisper
Command: npx skills add https://github.com/chrishuffman5/skills --skill whisper-chrishuffman5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai-whisper, transformers, torch, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill transforms spoken words into text with high accuracy, making it easier to transcribe podcasts, videos, meetings, and more in a wide range of languages.

Core Features & Use Cases

Speech Recognition: Supports transcription in over 90 languages and dialects.
Model Customization: Choose from six model sizes to balance speed and accuracy.
Multilingual Processing: Ideal for users requiring language-specific functionality and translation.

Quick Start

Install the Whisper skill and run the transcribe command on an audio file using whisper "audio.mp3".

Frequently Asked Questions about whisper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe an audio file to text using speech recognition?▼

To transcribe audio to text, you can run the transcribe command on an audio file using `whisper "audio.mp3"`. This speech recognition process leverages the Whisper ASR model to automatically convert spoken words into high-precision text.

Does Whisper speech to text support multiple languages and dialects?▼

Whisper speech to text supports transcription in over 90 languages and dialects. It provides multilingual processing functionality, allowing you to transcribe meetings, lectures, and audio books across diverse spoken languages with high precision.

Can I balance speed and accuracy when using ASR for audio transcription?▼

You can balance speed and accuracy for audio transcription by choosing from six Whisper ASR model sizes. This customization allows you to optimize the automatic speech recognition processing based on your specific application requirements.

Do I need PyTorch and Transformers installed for automatic speech recognition?▼

You need PyTorch, Transformers, and openai-whisper dependencies installed to run this automatic speech recognition Skill. These frameworks provide the necessary machine learning infrastructure to execute the Whisper ASR model for text transcription.

What is the best way to transcribe meetings and lectures offline?▼

The best way to transcribe meetings and lectures offline is using the Whisper ASR model, which provides both real-time and offline speech to text processing. It deploys locally to transcribe audio files with high precision across multiple languages.