whisper

Name: whisper
Availability: InStock
Author: Quill-Agent

Transcribe spoken audio into text across 99 languages.

3|1|Updated May 19, 2026

Search Tags:#speech recognition #transcription #audio processing #multilingual #ASR

Ready to run

npx skills add https://github.com/Quill-Agent/Quill-Agent --skill whisper-quill-agent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/Quill-Agent/Quill-Agent/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/Quill-Agent/Quill-Agent --skill whisper-quill-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai-whisper, transformers, torch, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the process of converting spoken language into written text, with support for a wide range of languages and transcription options.

Core Features & Use Cases

Multilingual Speech Recognition: Transcribe audio in 99 different languages.
Flexible Model Sizes: Offers a variety of model sizes from tiny to large, suitable for different use cases.
Use Case: For instance, you can use this Skill to automatically transcribe a multilingual conference, making the content accessible to a wider audience.

Quick Start

Install the whisper skill and transcribe your audio file with the command 'whisper transcribe audio.mp3'.

Frequently Asked Questions about whisper

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

FAQPage Schema

How do I transcribe audio files into text using speech recognition?▼

You can transcribe spoken audio into text by installing this Skill and running the transcription command on your audio file, utilizing openai-whisper, transformers, and torch libraries for audio processing.

Does multilingual speech recognition support transcription in my specific language?▼

Multilingual speech recognition supports transcribing audio in 99 different languages, allowing you to process diverse media and international meetings into accessible written text.

Can I use different model sizes for audio transcription depending on my use case?▼

Audio transcription offers flexible model sizes ranging from tiny to large, allowing you to balance processing speed and accuracy based on your specific audio quality and transcription requirements.

Do I need to install torch and transformers to process speech-to-text?▼

Yes, processing speech-to-text requires installing openai-whisper, transformers, and torch libraries, as these dependencies provide the necessary framework for audio processing and transcription execution.

What is the best way to automate meeting notes and podcast transcription?▼

Automating meeting notes and podcast transcription requires speech-to-text functionality, which automatically converts spoken audio into written text, ideal for processing varying audio qualities and multilingual content.

What are the limitations of transcribing low-quality audio with speech recognition?▼

While this Skill supports a wide array of audio qualities, transcribing low-quality audio may require larger model sizes to improve accuracy, which increases processing time and computational resource demands.