whisper

Name: whisper
Availability: InStock
Author: zangjeicy

Transcribe multilingual audio to text using OpenAI's Whisper model.

Updated Jul 13, 2026

Search Tags:#transcription #whisper #audio #multilingual #speech-to-text #asr

Ready to run

npx skills add https://github.com/zangjeicy/Hermes --skill whisper-zangjeicy

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the challenge of converting spoken audio into accurate, searchable text across 99 different languages, eliminating the need for manual transcription.

Core Features & Use Cases

Multilingual Transcription: Supports 99 languages with robust performance even in noisy environments.
Translation & Identification: Automatically detects the source language and can translate audio directly into English text.
Use Case: Use this to transcribe long-form podcast episodes, automate meeting minutes, or generate subtitles for video content efficiently.

Quick Start

Use the whisper skill to transcribe the audio file named meeting_recording.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 an audio file to text using Whisper?▼

To convert spoken audio to searchable text, this Skill uses OpenAI's Whisper model to perform robust multilingual speech recognition and high-performance audio-to-text conversion.

Can I transcribe speech in multiple languages or noisy environments?▼

Yes, multilingual transcription supports 99 languages with robust performance even in noisy environments, automatically detecting the source language and optionally translating spoken audio directly into English text.

Do I need torch and transformers to run speech-to-text conversion?▼

Yes, executing high-performance speech-to-text conversion requires integration with torch, transformers, and openai-whisper dependencies to run the robust multilingual speech recognition model.

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

Automating meeting minutes and podcast transcription involves processing long-form audio files through the multilingual speech recognition model to generate accurate, searchable text outputs.

Does the speech-to-text model support real-time language identification?▼

Yes, the speech recognition model supports real-time language identification alongside robust multilingual transcription, automatically detecting the source language across 99 different languages.