whisper-asr

Transcribe audio files locally using Whisper models via Whisper.cpp.

1|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/imchangchang/skills-registry --skill whisper-asr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper-asr
Source: https://github.com/imchangchang/skills-registry/tree/main/skills/domains/ai/whisper-asr
Command: npx skills add https://github.com/imchangchang/skills-registry --skill whisper-asr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a robust solution for converting spoken audio into written text locally, ensuring data privacy and reducing reliance on external APIs.

Core Features & Use Cases

  • Local Speech-to-Text: Transcribe audio files directly on your machine without sending data to the cloud.
  • Model Selection: Choose from various Whisper models (tiny, base, small, medium, large) to balance speed and accuracy.
  • Performance Optimization: Guidance on leveraging GPU acceleration and pre-processing audio for better results.
  • Use Case: Transcribe sensitive meeting recordings or process a large batch of audio files for analysis while maintaining complete data confidentiality.

Quick Start

Use the whisper-asr skill to transcribe the audio file named 'meeting_recording.wav' using the medium model.

Frequently Asked Questions about whisper-asr

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

FAQPage Schema
When should I avoid using cloud APIs for speech-to-text transcription?

You should avoid cloud APIs for speech-to-text when handling sensitive meeting recordings or processing confidential audio data. Local deployment ensures complete data privacy and reduces reliance on external services for transcription tasks.

What is the best way to balance speed and accuracy when transcribing audio with Whisper?

Balancing speed and accuracy in speech-to-text requires selecting from various Whisper models like tiny, base, small, medium, or large. Smaller models provide faster processing, while larger models deliver enhanced transcription accuracy for complex audio.

Can I use GPU acceleration to improve local audio transcription performance?

GPU acceleration significantly improves local audio transcription performance by optimizing processing speed. You can leverage hardware acceleration alongside audio pre-processing techniques to achieve faster and more accurate speech-to-text results.

Does local speech-to-text support batch transcription for multiple audio file formats?

Local speech-to-text supports batch transcription across various audio file formats. You can process multiple audio files simultaneously for large-scale analysis tasks while maintaining complete data confidentiality throughout the workflow.

When should I avoid using cloud APIs for speech-to-text transcription?

You should avoid cloud APIs for speech-to-text when handling sensitive meeting recordings or processing confidential audio data. Local deployment ensures complete data privacy and reduces reliance on external services for transcription tasks.