skills.rest
519lab
519labOFFICIAL
Explore all skills by this author →
WebsiteGitHub

whisper

Transcribe and translate speech to text using OpenAI's Whisper model.

2|Updated May 22, 2026
Search Tags:#translation#speech recognition#transcription#openai#multilingual
One-click install
npx skills add https://github.com/519lab/thoth-agent --skill whisper-519lab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/519lab/thoth-agent/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/519lab/thoth-agent --skill whisper-519lab

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 provides robust speech recognition capabilities, allowing users to transcribe and translate spoken language into text, supporting a wide range of languages and model sizes.

Core Features & Use Cases

  • Multilingual Speech Recognition: Supports 99 languages with transcription, translation to English, and language identification.
  • Model Sizes: Offers six model sizes from tiny to large, catering to different needs for speed and quality.
  • Use Case: Ideal for use cases such as speech-to-text transcription, podcast/video transcription, meeting notes automation, and multilingual audio processing.

Quick Start

Install the whisper skill and transcribe an audio file using the command: 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 OpenAI Whisper?▼

You can transcribe speech to text by running the `whisper audio.mp3` command. This Skill uses the OpenAI Whisper model to process audio files and generate accurate written transcriptions.

Can I translate multilingual audio to English text automatically?▼

Yes, this Skill supports multilingual speech recognition and translates spoken audio to English text. It identifies the source language and processes the audio using the Whisper model to generate English output.

Does speech recognition with Whisper support different model sizes?▼

Yes, Whisper offers six model sizes from tiny to large. You can select the appropriate model size to balance transcription speed and quality based on your available computing resources and accuracy needs.

Do I need PyTorch and Transformers installed for audio transcription?▼

Yes, audio transcription requires torch and transformers libraries. The Skill depends on openai-whisper, transformers, and torch to execute the speech recognition models and process audio data into text.

What is the best way to automate meeting notes and podcast transcription?▼

Automating meeting notes and podcast transcription is achieved by processing audio files through OpenAI Whisper. The Skill transcribes spoken content into text, handling multilingual audio to streamline documentation and content creation.

Related Skills

Explore More Data & Analytics Skills→
zeronx798zeronx798

whisper

Transcribe multilingual audio files into text using OpenAI's Whisper model.

Community
Intermediate
horisanLoghorisanLog

generate

Generate Miro-compatible business flow diagrams from text inputs.

Community
Advanced
davpatel605-beepdavpatel605-beep

whisper

Transcribe spoken audio into timestamped text across 99 languages.

Community
Intermediate
TikTzukiTikTzuki

Google Cloud Text-to-Speech

Convert text to speech and transcribe audio via cloud APIs.

Community
Advanced