ASR

Convert spoken audio in WAV and MP3 formats into written text transcriptions.

1|Updated May 1, 2026
One-click install
npx skills add https://github.com/e2662020/QuickMovie --skill asr-e2662020
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/e2662020/QuickMovie/tree/main/skills/ASR
Command: npx skills add https://github.com/e2662020/QuickMovie --skill asr-e2662020

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually transcribing audio content from meetings, interviews, podcasts, and voice notes is extremely time-consuming, labor-intensive, and prone to human error. This Skill automates the process to deliver fast, accurate text transcriptions of spoken audio with minimal effort.

Core Features & Use Cases

  • Multi-format audio support: Transcribes common audio formats including WAV, MP3, M4A, FLAC, and OGG files without manual format conversion.
  • Flexible input options: Accepts both local audio file paths and base64 encoded audio data for processing.
  • Dual usage modes: Offers a simple command-line interface for quick one-off transcriptions and a full software development kit for integration into custom applications and automated workflows.
  • Common use cases: Meeting documentation, interview analysis, podcast content creation, voice note digitization, call center analytics, and accessibility feature development.

Quick Start

Use the ASR skill to transcribe the audio file 'team_weekly_meeting.wav' into a readable, accurate text transcript.

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe speech audio to text from a local WAV or MP3 file?

To transcribe speech audio to text, you can use this Skill's command-line interface for quick transcriptions or its software development kit to process local WAV and MP3 file paths programmatically.

Can I use base64 encoded audio data for automated speech-to-text processing?

Yes, you can use base64 encoded audio data for speech-to-text processing. The Skill accepts base64 encoded inputs in common audio formats, enabling automated workflows without needing direct file path access.

Do I need the z-ai-web-dev-sdk package to run audio transcription tasks?

Yes, you need the z-ai-web-dev-sdk package installed to run audio transcription tasks. This dependency is required for the Skill to convert spoken audio content into written text transcriptions.

What audio formats are supported for voice-to-text conversion?

The voice-to-text conversion supports common audio formats including WAV, MP3, M4A, FLAC, and OGG files, allowing you to transcribe spoken audio content without needing any manual format conversion.

What is the best way to automate meeting documentation and podcast transcription?

The best way to automate meeting documentation and podcast transcription is using this Skill's software development kit to integrate audio processing into custom applications, converting spoken audio content into accurate written text automatically.

Are there limitations when processing large audio files for speech-to-text conversion?

The metadata does not specify explicit file size limitations for speech-to-text conversion. It supports common formats like WAV and MP3, accepting both local file paths and base64 encoded audio data for processing.