whisper

Transcribe spoken audio to text and translate it to English using OpenAI's Whisper model.

Updated May 8, 2026

Search Tags:#translation #speech recognition #transcription #audio processing #asr

Ready to run

npx skills add https://github.com/superfhp/lumi-agent --skill whisper-superfhp

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/superfhp/lumi-agent/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/superfhp/lumi-agent --skill whisper-superfhp

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 simplifies speech-to-text transcription, translation to English, and multilingual audio processing with OpenAI's Whisper model.

Core Features & Use Cases

Speech-to-Text: Accurately transcribe speech from 99 languages to text.
Translation: Convert audio to English and other languages.
Multilingual Support: Handle audio in various languages with high accuracy.
Use Case: Ideal for automating podcast and video transcriptions, meeting notes, or multilingual audio content processing.

Quick Start

Transcribe 'meeting_notes.mp3' with Whisper using the 'whisper' skill.

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 OpenAI's Whisper model?▼

Whisper transcribes spoken audio files into text by leveraging OpenAI's ASR model. It supports automated transcription across 99 languages for tasks like generating meeting notes or podcast transcriptions.

Can I translate multilingual speech to English automatically?▼

Whisper translates multilingual speech to English by processing audio input and generating English text output. This works across 99 languages for multilingual audio content processing and translation.

Do I need torch and transformers to run speech recognition with Whisper?▼

Yes, running speech recognition with Whisper requires installing torch and transformers. The Skill depends on openai-whisper, transformers, and torch to execute ASR transcription and audio processing tasks.

What is the best way to automate meeting notes transcription from audio?▼

Automating meeting notes transcription is best achieved using Whisper's ASR model to convert spoken audio to text. It processes audio files like meeting_notes.mp3 and outputs accurate written transcriptions.

Does speech recognition work for audio files in multiple languages?▼

Speech recognition with Whisper supports audio files in 99 languages. It accurately transcribes multilingual audio to text and translates spoken content to English for multilingual audio content processing.