whisper

Transcribe audio into multilingual text with optional English translation.

1|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/cryptopafi/nexusos-skills --skill whisper-cryptopafi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/cryptopafi/nexusos-skills/tree/main/mlops/models/whisper
Command: npx skills add https://github.com/cryptopafi/nexusos-skills --skill whisper-cryptopafi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transcribes audio into accurate multilingual text, enabling quick capture of spoken content across languages for research, documentation, and accessibility.

Core Features & Use Cases

  • 99-language transcription and language identification for robust multilingual processing.
  • Translation to English and podcast/meeting transcription use cases for multilingual teams.
  • Flexible model sizes (tiny to large) to balance speed and accuracy.
  • Real-world example: transcribe a multilingual podcast with automatic language detection and English translation.

Quick Start

Install Whisper and transcribe an audio file to produce a multilingual text transcript.

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 with automatic language detection?

Audio transcription with automatic language detection identifies the spoken language from the audio file and converts it into accurate multilingual text. It supports 99 languages and optionally translates the result to English.

How does multilingual speech recognition translate audio to English?

Multilingual speech recognition processes the audio input, identifies the source language, and transcribes the spoken content. It optionally translates the generated text transcript into English across 99 supported languages.

Do I need FFmpeg and Python to process audio for transcription?

Yes, audio processing for transcription requires Python along with specific dependencies like openai-whisper, transformers, and torch. FFmpeg is also required to handle the audio file decoding before speech recognition occurs.

What is the best way to transcribe a multilingual podcast for my team?

Transcribing a multilingual podcast involves processing the audio file to detect spoken languages and generate a text transcript. Flexible model sizes balance processing speed and accuracy for podcast and meeting transcription use cases.

Can I adjust speech recognition accuracy and speed for audio transcription?

Audio transcription allows you to adjust accuracy and speed by selecting flexible model sizes ranging from tiny to large. This balances the speech recognition processing speed against the text transcript output accuracy.

What are the limitations of using machine learning for audio transcription?

Machine learning audio transcription requires selecting a model size that balances speed and accuracy. Processing large audio files requires dependencies like torch and FFmpeg, which may demand significant computational resources.