Qwen3 ASR — Voice Transcription

Community

Transcribe speech to text locally with Qwen3-ASR.

Authornaveencreation
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Transcribing speech from audio files can be time-consuming and error-prone when done manually. This skill provides a self-contained workflow to convert spoken language into text using the Qwen3-ASR model, enabling faster transcription and offline processing.

Core Features & Use Cases

  • Transcribes audio files to text using the Qwen3-ASR-0.6B model.
  • Supports commonly used audio formats (WAV, MP3, M4A, FLAC, OGG) and automatically handles sampling rate conversion.
  • Use cases include meeting transcription, podcast notes, and archival of audio content for search and indexing.

Quick Start

Run the asr script with the model directory and an audio file to obtain the transcription.

Dependency Matrix

Required Modules

curlunzipbash

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Qwen3 ASR — Voice Transcription
Download link: https://github.com/naveencreation/rustscribe/archive/main.zip#qwen3-asr-voice-transcription

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.