whisper

Transcribe audio from 99 languages and translate it to English.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/hochoa13/Asistente-Harlest --skill whisper-hochoa13
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/hochoa13/Asistente-Harlest/tree/main/skills/mlops/models/whisper
Command: npx skills add https://github.com/hochoa13/Asistente-Harlest --skill whisper-hochoa13

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the conversion of spoken audio into written text and translates it into English, making audio content accessible and searchable.

Core Features & Use Cases

  • Multilingual Transcription: Transcribes audio from 99 different languages into text.
  • Translation to English: Translates spoken content from various languages directly into English text.
  • Use Case: Automatically transcribe a multilingual podcast episode, generating accurate subtitles and a searchable transcript.

Quick Start

Use the whisper skill to transcribe the audio file 'meeting.mp3' and save the output as a text file.

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 speech recognition?

Speech recognition transcribes spoken audio into text using OpenAI's Whisper model. This Skill supports robust audio processing across 99 languages, allowing you to transcribe files like meeting recordings and save the output as searchable text.

Can I translate multilingual audio directly to English text?

You can translate multilingual audio directly to English text using the Whisper model. It processes spoken content from 99 different languages and outputs the translated English text, making foreign language audio accessible and searchable.

Does speech recognition with Whisper require PyTorch and Transformers installed?

Yes, speech recognition with Whisper requires PyTorch and Transformers installed. The Skill explicitly depends on the openai-whisper, transformers, and torch libraries to perform audio processing and automatic speech recognition tasks.

What is the best way to generate subtitles for a multilingual podcast?

The best way to generate subtitles for a multilingual podcast is using Whisper for automatic speech recognition. It transcribes audio from 99 languages into text and can translate spoken content directly into English, creating accurate subtitle files.

How do I select different Whisper model sizes for varying transcription performance needs?

Selecting different Whisper model sizes adjusts transcription performance and resource usage. The Skill supports various model sizes, allowing you to balance speed and accuracy when processing audio files for speech recognition and translation tasks.