whisper

Transcribe and translate multilingual audio to text using openai-whisper.

1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/nelohenriq/hermes-agent-plus --skill whisper-nelohenriq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/nelohenriq/hermes-agent-plus/tree/main/skills/mlops/models/whisper
Command: npx skills add https://github.com/nelohenriq/hermes-agent-plus --skill whisper-nelohenriq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes audio into text across 99 languages with language identification and optional translation, enabling accessible, searchable content.

Core Features & Use Cases

  • Multilingual speech-to-text transcription for podcasts, videos, meetings, and accessibility needs.
  • Language identification and translation to English when needed.
  • Model-size options (tiny to large) to balance speed and accuracy for offline or cloud use.

Quick Start

Install Whisper and run a quick transcription on an audio file to see results.

Frequently Asked Questions about whisper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio to text in multiple languages?

To transcribe audio to text in multiple languages, you can use speech recognition models like Whisper to automatically identify the spoken language and convert audio files into searchable text across 99 supported languages.

Can I translate speech to English during audio transcription?

Yes, speech to English translation can be performed during audio transcription. The process identifies the original spoken language and provides optional translation to English alongside the text output for media localization needs.

Do I need a GPU for accurate multilingual speech recognition?

A GPU is not strictly required for multilingual speech recognition but is recommended for best performance. Optional GPU acceleration significantly speeds up audio processing, especially when using larger model sizes for higher accuracy.

What is the best way to generate meeting notes from audio recordings?

The best way to generate meeting notes from audio recordings is through automated speech-to-text transcription. This converts spoken discussions into searchable text, enabling accessible documentation and easy review of podcast or meeting workflows.

How do I balance speed and accuracy when transcribing podcasts?

To balance speed and accuracy when transcribing podcasts, select between different AI model sizes ranging from tiny to large. Smaller models process audio faster, while larger models provide higher transcription accuracy for offline or cloud environments.