skills.rest
23f2001390
23f2001390COMMUNITY
Explore all skills by this author →
GitHub

Qwen3 ASR — Voice Transcription

Transcribe audio files to text locally using the Qwen3-ASR-0.6B model.

Updated Mar 6, 2026
Search Tags:#rust#speech-to-text#windows#asr#voice-transcription#local-inference
One-click install
npx skills add https://github.com/23f2001390/qwen3-asr-rust-cpu-windows --skill qwen3-asr-voice-transcription-23f2001390
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Qwen3 ASR — Voice Transcription
Source: https://github.com/23f2001390/qwen3-asr-rust-cpu-windows/tree/main/skills
Command: npx skills add https://github.com/23f2001390/qwen3-asr-rust-cpu-windows --skill qwen3-asr-voice-transcription-23f2001390

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires huggingface_hub, transformers, curl, unzip, bash, python3, pip.

What problem does it solve?

Transcribe speech from audio files to text.

Core Features & Use Cases

  • Local transcription of audio formats to text using a Rust CLI.
  • Model management and offline operation with Qwen3-ASR-0.6B.
  • Use cases include transcribing meetings, memos, and podcasts for quick text results.

Quick Start

Run the asr binary with the model directory and an audio file to print the transcription.

Frequently Asked Questions about Qwen3 ASR — Voice Transcription

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

FAQPage Schema
How do I transcribe audio to text locally on Windows?▼

To transcribe audio locally on Windows, this Skill runs a Rust-based CLI with the Qwen3-ASR-0.6B model. It automatically resamples any FFmpeg-compatible audio format to 16 kHz mono and outputs the text transcription directly to stdout.

Can I use this voice transcription tool for meeting recordings and podcasts?▼

Yes, this voice transcription tool processes meeting recordings, voice memos, and podcasts. It decodes any FFmpeg-compatible audio format locally using the Qwen3-ASR-0.6B model to provide quick text results.

Do I need an internet connection for local speech-to-text inference?▼

No, local speech-to-text inference operates offline once the model is downloaded. It uses the Qwen3-ASR-0.6B model directory and a Rust asr binary to transcribe audio without requiring continuous internet access.

What audio formats are supported by this local ASR pipeline?▼

This local ASR pipeline supports all FFmpeg-compatible audio formats. It handles audio preprocessing by automatically resampling the input files to 16 kHz mono before transcribing them with the Qwen3-ASR-0.6B model.

How do I run the asr binary to get my audio transcription?▼

To get your audio transcription, run the asr binary from the command line with the model directory path and your audio file. The tool will decode the audio and print the resulting text directly to stdout.

Does this speech-to-text tool require Python and pip to set up?▼

Yes, setup requires Python3 and pip along with dependencies like huggingface_hub and transformers. These are used to manage the Qwen3-ASR-0.6B model before running the Rust-based asr binary for transcription.

Related Skills

Explore More Software Engineering Skills→
naveencreationnaveencreation

Qwen3 ASR — Voice Transcription

Transcribe audio files to text using the Qwen3-ASR-0.6B model.

Community
Advanced
junghan0611junghan0611
6

transcribe

Transcribe audio files to plain text via the Groq Whisper API.

Community
Intermediate
zhangdszqzhangdszq
1

ffmpeg-usage

Automate FFmpeg multimedia conversion, compression, and batch processing workflows.

Community
Advanced
augustsclaugustscl
2

asr

Transcribe audio files into text using local speech recognition models.

Community
Intermediate