whisper

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

Updated Jul 13, 2026
One-click install
npx skills add https://github.com/zeronx798/demo-hermes-agent --skill whisper-zeronx798
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/zeronx798/demo-hermes-agent/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/zeronx798/demo-hermes-agent --skill whisper-zeronx798

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.

Core Features & Use Cases

  • Multilingual Transcription: Supports 99 languages with high accuracy for meetings, podcasts, and interviews.
  • Translation & Identification: Automatically detects languages and translates non-English audio into English text.
  • Use Case: Use this to transcribe a multi-hour technical podcast into a structured text document or to generate subtitles for video content automatically.

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 multilingual audio files into text automatically?

You can transcribe multilingual audio files into text by using OpenAI's Whisper model, which supports 99 different languages and automatically detects the spoken language to generate accurate text.

Can I automatically translate non-English speech-to-text audio into English?

Yes, speech-to-text translation is supported. The Whisper model automatically identifies non-English audio and translates the spoken content into English text for diverse audio formats.

What Python dependencies do I need for local speech-to-text transcription?

Local speech-to-text transcription requires a Python environment with torch, transformers, and openai-whisper dependencies installed to execute the Whisper model.

Does Whisper speech-to-text work for transcribing long technical podcasts?

Whisper handles speech-to-text transcription for multi-hour technical podcasts and interviews, converting extensive audio recordings into structured text documents with high accuracy.

What is the best way to generate subtitles from audio for video content?

The best way to generate subtitles from audio is using multilingual speech-to-text transcription, which processes diverse audio formats to produce timestamped text suitable for video content.

Are there limitations when using local ASR for multilingual transcription?

Local ASR multilingual transcription requires sufficient computational resources to run torch and transformers, and processing multi-hour audio files may take significant time depending on hardware.