whisper

Transcribe and translate audio files into text using OpenAI Whisper.

1|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/icyzh/hermes-web --skill whisper-icyzh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/icyzh/hermes-web/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/icyzh/hermes-web --skill whisper-icyzh

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, timestamped text across 99 different languages, eliminating the need for manual transcription or expensive third-party services.

Core Features & Use Cases

  • Multilingual Transcription: Transcribe audio files in 99 languages with high accuracy.
  • Translation: Automatically translate non-English audio directly into English text.
  • Use Case: Use this skill to process meeting recordings, podcasts, or video interviews to generate searchable transcripts, subtitles, or meeting summaries.

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 audio files into text using the Whisper model?

Transcribe audio files into text by loading the Whisper model to process local speech-to-text tasks. Provide an audio file like an mp3, and the model outputs timestamped multilingual text.

Can Whisper translate non-English audio into English text directly?

Whisper translates non-English audio directly into English text during the speech-to-text process. It automatically detects the spoken language and outputs the translated English transcription.

Do I need ffmpeg and Python to run local speech-to-text transcription?

Local speech-to-text transcription requires Python 3.8-3.11, ffmpeg, and the openai-whisper library installed. These dependencies handle audio processing and model execution for accurate multilingual transcription.

What is the best way to generate subtitles from podcast recordings?

Generate subtitles from podcast recordings by processing the audio files through the Whisper model. This multilingual speech recognition approach transcribes the spoken content into timestamped text suitable for subtitle generation.

Does the Whisper speech recognition model support meeting documentation?

Whisper speech recognition supports meeting documentation by transcribing meeting recordings into searchable text. It accurately processes multilingual audio to create structured text outputs and meeting summaries.

What languages does multilingual speech recognition support for transcription?

Multilingual speech recognition supports transcription across 99 different languages using the Whisper model. It handles diverse audio files for high-accuracy multilingual speech processing and translation.