Productivity
qwen-asr avatar

qwen-asr

Transcribe audio files (wav, mp3, ogg) to text using the Qwen ASR model. Fast, local-friendly, and requires no API keys.

Introduction

Qwen ASR is a versatile speech-to-text tool designed for developers and power users who need to convert audio recordings into transcripts efficiently. By leveraging the Qwen ASR Demo service, this skill provides a streamlined interface for processing various audio formats, including wav, mp3, and ogg files. It is an ideal solution for automating meeting notes, processing voice messages, or indexing audio content within an AI agent workflow without the overhead of managing complex authentication or paid API services. The skill is built to integrate seamlessly into your local development environment using standard shell commands.

  • Multi-language support for diverse global content.

  • Lightweight architecture that requires no configuration or API key management.

  • Direct command-line integration, allowing for piping input directly into text files.

  • High-performance transcription based on the proven Qwen speech-to-text model.

  • Cross-platform compatibility for local processing of audio-to-text tasks.

  • Input: Supports standard audio formats including .wav, .mp3, and .ogg files.

  • Output: Generates clear, text-based transcripts which can be redirected to .txt files or passed to subsequent LLM processing chains.

  • Usage: Execute the transcription via the provided uv-managed script, e.g., uv run scripts/main.py -f audio.wav.

  • Constraints: Relies on the Qwen ASR Demo service endpoints; ensure your environment has basic Python dependencies installed.

  • Best practices: Use this for quick, on-demand transcription of short-to-medium length audio clips or voice messages sent by users within an agentic interaction.

Repository Stats

Stars
4,456
Forks
1,215
Open Issues
7
Language
Python
Default Branch
main
Sync Status
Idle
Last Synced
Apr 30, 2026, 12:00 PM
View on GitHub