whisper

Convert spoken audio into written text using the openai-whisper library.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/hhhi21g/HealthCenter --skill whisper-hhhi21g
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/hhhi21g/HealthCenter/tree/main/.codex/skills/whisper
Command: npx skills add https://github.com/hhhi21g/HealthCenter --skill whisper-hhhi21g

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill transforms spoken language into written text, making audio content easily accessible and editable.

Core Features & Use Cases

  • Multilingual Support: Transcribe speech from 99 languages, including English, Spanish, French, German, and more.
  • Accurate Transcription: Achieve high-quality transcriptions with models designed for different scenarios and languages.
  • Use Case: Ideal for transcribing podcasts, videos, lectures, and interviews, making audio content easily searchable and editable.

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 into written text automatically?▼

You can transcribe audio files into written text by using an automatic speech recognition library like openai-whisper. This skill processes spoken audio and converts it into editable text, handling formats like MP3 for direct transcription.

Can I use speech-to-text processing for multiple languages?▼

Yes, multilingual speech-to-text processing supports 99 languages, including English, Spanish, French, and German. It uses robust automatic speech recognition models designed for different linguistic scenarios to achieve accurate transcriptions.

Do I need ffmpeg installed to convert speech to text?▼

Yes, ffmpeg is required as a dependency to convert speech to text using this skill. Along with openai-whisper, torch, and transformers, ffmpeg handles the underlying audio processing required for accurate automatic speech recognition.

What is the best way to generate subtitles from a podcast or video?▼

The best way to generate subtitles from a podcast or video is using ASR models like openai-whisper. This skill provides various model sizes tailored for different use cases, converting spoken audio content into searchable, editable text.

How does automatic speech recognition handle different audio processing scenarios?▼

Automatic speech recognition handles different audio processing scenarios by offering various model sizes. This allows the transcription process to balance resource usage and accuracy based on the specific audio content and language requirements.

Are there limitations when transcribing long meetings with openai-whisper?▼

When transcribing long meetings with openai-whisper, limitations may arise from hardware constraints due to torch dependency. Selecting appropriate model sizes is necessary to manage processing loads and ensure successful speech-to-text conversion.