whisper

Transcribe multilingual audio to text across 99 languages.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/1thirteeng3/greenmoire --skill whisper-1thirteeng3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/1thirteeng3/greenmoire/tree/main/integrations/hermes-agent/skills/mlops/models/whisper
Command: npx skills add https://github.com/1thirteeng3/greenmoire --skill whisper-1thirteeng3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transcribing multilingual audio into accurate text is time-consuming and error-prone when done manually, especially across many languages. Whisper provides robust transcription and translation capabilities, enabling seamless capture of spoken content for accessibility, indexing, and content repurposing.

Core Features & Use Cases

  • Multilingual speech-to-text transcription across 99 languages with optional language identification and translation to English.
  • Model size selection and hardware-aware deployment (tiny to large) for CPU or GPU environments.
  • Practical use cases include podcast transcripts, video captions, meeting notes automation, and multilingual content processing.

Quick Start

Transcribe a sample audio file to test Whisper's capabilities.

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 to text across different languages?

To transcribe multilingual audio to text, specify the target language or enable automatic language identification to generate accurate text outputs across 99 supported languages.

Can I translate spoken audio to English text automatically?

Yes, you can translate spoken audio to English text by enabling the translation task, which processes multilingual speech inputs and outputs the corresponding English text.

How do I generate timestamped outputs for podcast transcription?

To generate timestamped outputs for podcast transcription, enable the optional timestamp feature during processing, which aligns the generated text segments with precise audio timings.

Does speech recognition model size affect CPU or GPU hardware deployment?

Yes, speech recognition model size affects hardware deployment; you can select from tiny to large models based on your CPU or GPU environment to optimize processing efficiency.

What is the best way to improve video captions accuracy using initial prompts?

To improve video captions accuracy, provide an initial prompt containing specific vocabulary or context, which guides the speech recognition model to produce more accurate transcriptions.