whisper

Transcribe multilingual audio into text and translate to English.

2|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/CUexter/hermes-agent --skill whisper-cuexter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/CUexter/hermes-agent/tree/main/skills/mlops/models/whisper
Command: npx skills add https://github.com/CUexter/hermes-agent --skill whisper-cuexter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Whisper provides reliable, multilingual speech recognition to turn audio into text with high accuracy across 99 languages, plus translation capabilities when needed.

Core Features & Use Cases

  • Multilingual transcription: Transcribes audio in 99 languages to text.
  • Translation to English: Translates non-English transcripts into English.
  • Language identification: Detects the language of input audio and adapts transcription accordingly.
  • Flexible model options: Supports multiple Whisper model sizes (tiny, base, small, medium, large, turbo) for speed and accuracy.

Quick Start

Install the Whisper package and run a transcription on an audio file to produce text.

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 from podcasts or meetings into text?

To transcribe multilingual audio, you load a Whisper model and process the input file. The speech recognition system detects the language and accurately converts the spoken audio into text without requiring manual language selection.

Can I automatically translate non-English audio files into English text?

Yes, you can translate non-English audio into English text. The multilingual speech-to-text process transcribes the original spoken audio and simultaneously translates the resulting transcript directly into English.

What is the best way to balance transcription speed and accuracy?

You balance transcription speed and accuracy by selecting a specific Whisper model size. Flexible model options range from tiny and base for faster processing to medium, large, and turbo configurations for higher accuracy results.

Does multilingual speech recognition support audio across 99 languages?

Yes, multilingual speech recognition supports audio processing across 99 languages. The system identifies the spoken language from the input audio and adapts the transcription workflow accordingly for accurate text conversion.

When do I need to manually select a language for audio transcription?

You need to manually select a language for audio transcription when the automatic language identification might struggle with mixed-language audio. Specifying the language explicitly ensures the speech-to-text model applies the correct transcription parameters.