asr-transcribe-to-text

Transcribe audio and video files to text using Qwen3-ASR.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/HuuBar/skill-routing-experiment --skill asr-transcribe-to-text
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: asr-transcribe-to-text
Source: https://github.com/HuuBar/skill-routing-experiment/tree/main/unified_skills/daymade/asr-transcribe-to-text
Command: npx skills add https://github.com/HuuBar/skill-routing-experiment --skill asr-transcribe-to-text

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mlx-audio>=0.3.1, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Transcribes audio and video files to text using Qwen3-ASR, enabling quick access to spoken content for search, notes, and analysis.

Core Features & Use Cases

  • Dual-mode transcription: local MLX on Apple Silicon for offline, or remote API for scalable cloud processing.
  • Auto-detection and path optimization: automatically chooses the best path and persists configuration for future sessions.
  • Use Case: Meetings, lectures, interviews, podcasts, screen recordings, and any audio/video file that needs text.

Quick Start

Provide the path to an audio or video file to begin transcription using Qwen3-ASR with automatic mode selection.

Frequently Asked Questions about asr-transcribe-to-text

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

FAQPage Schema
How do I transcribe audio and video files to text using Qwen3-ASR?

Yes, you can transcribe audio and video offline using local MLX mode on Apple Silicon devices, which automatically optimizes the path and persists your configuration for future offline speech-to-text sessions.

Does this speech-to-text tool support remote API processing?

Yes, this speech-to-text tool supports remote API processing, enabling scalable cloud transcription for audio and video files when local resources are limited or when handling large volumes of recordings.

Can I use ASR transcription for screen recordings and interviews?

Yes, you can use ASR transcription for screen recordings and interviews, as the tool quickly converts spoken content into text for easy search, note-taking, and analysis across various media formats.

Do I need an Apple Silicon device for local MLX audio transcription?

Yes, you need an Apple Silicon device for local MLX audio transcription, because the local inference path relies on the mlx-audio dependency to process speech-to-text tasks offline with platform auto-detection.

What is the best way to automatically switch between local and remote ASR?

The best way to switch between local and remote ASR is using the built-in platform auto-detection, which automatically chooses the optimal transcription path and persists the configuration for your future sessions.