ASR

Transcribe spoken audio from files into text documents.

Updated Feb 13, 2026
One-click install
npx skills add https://github.com/Munreader/M-nreader --skill asr-munreader
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/Munreader/M-nreader/tree/main/skills/ASR
Command: npx skills add https://github.com/Munreader/M-nreader --skill asr-munreader

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, fs, and includes scripts (resource) components.

What problem does it solve?

Converts spoken audio into written text, enabling transcription and voice-controlled features.

Core Features & Use Cases

  • Audio transcription from files or base64-encoded audio for applications like note-taking, transcription services, and voice interfaces.
  • Supports multiple formats such as WAV, MP3, and M4A, facilitating integration across various audio sources.
  • Use Case: Transcribe recorded meetings or interviews into text for documentation or analysis.

Quick Start

Transcribe an audio file by reading it, converting to base64, and calling the ASR API to get the text output.

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe an audio file to text for automated documentation?

Audio transcription converts spoken language from audio files or base64-encoded data into text documents. It processes WAV, MP3, and M4A formats for automated documentation and voice interface development.

Can I use speech-to-text transcription with MP3 and M4A audio formats?

Yes, speech-to-text transcription supports multiple formats including WAV, MP3, and M4A. This format compatibility facilitates integration across various audio sources for backend speech processing tasks.

What is the best way to convert recorded meetings into written text?

Converting recorded meetings into text involves reading the audio file and utilizing SDK functions to generate a text document. This provides accurate speech-to-text output for documentation and content analysis.

Does audio transcription work with base64-encoded audio data?

Yes, audio transcription processes base64-encoded audio data directly. You read your audio file, convert it to base64 format, and pass it to the SDK functions to receive the transcribed text output.

Do I need the z-ai-web-dev-sdk to perform voice transcription?

Yes, voice transcription requires the z-ai-web-dev-sdk dependency to process audio data. The Skill utilizes SDK functions from this package to transcribe spoken language from audio files into text documents.