whisper

Transcribe spoken language to text using OpenAI's Whisper model.

Updated May 11, 2026
One-click install
npx skills add https://github.com/richardnguyen0715/keep-it-real --skill whisper-richardnguyen0715
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/richardnguyen0715/keep-it-real/tree/main/refer-projects/hermes-agent/optional-skills/mlops/whisper
Command: npx skills add https://github.com/richardnguyen0715/keep-it-real --skill whisper-richardnguyen0715

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of converting spoken language into written text, supporting a wide range of languages and providing accurate transcription.

Core Features & Use Cases

  • Multilingual Support: Transcribe speech in 99 languages.
  • Robust Accuracy: Achieve high-quality transcription for a variety of use cases.
  • Flexible Model Sizes: Choose from six model sizes to balance speed and quality.
  • Use Case: Automate the transcription of podcasts, meetings, and other audio content into text for easy reference and analysis.

Quick Start

Use the whisper skill to transcribe the audio file 'meeting.mp3'.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I transcribe audio files to text using OpenAI's Whisper model?

Yes, speech-to-text processing supports 99 languages using the Whisper model. This multilingual capability allows you to transcribe audio content in various languages without needing separate models for each language.

Do I need to install PyTorch and transformers to use Whisper for transcription?

Whisper offers six different model sizes for transcription, allowing you to balance processing speed and accuracy. You can select a smaller model for faster results or a larger one for higher quality transcripts depending on your needs.

What is the best way to automate podcast transcription with multilingual audio?

The best way to automate podcast transcription with multilingual audio is using a dedicated speech-to-text model like Whisper. It handles diverse languages and accents robustly, converting spoken content into text for easy reference and analysis.

Does Whisper speech-to-text work well for meeting transcription?

Yes, Whisper speech-to-text works well for meeting transcription by accurately converting recorded spoken discussions into written text. It is specifically optimized for transcribing meetings and other audio content into easily searchable text formats.