ASR

Transcribe base64-encoded audio from files or streams into plain text.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/lucasmattosped/Blueberry-Math-Analyzer- --skill asr-lucasmattosped
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/lucasmattosped/Blueberry-Math-Analyzer-/tree/main/ASR
Command: npx skills add https://github.com/lucasmattosped/Blueberry-Math-Analyzer- --skill asr-lucasmattosped

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribe spoken audio into text to enable searchable transcripts, voice interfaces, and audio analytics.

Core Features & Use Cases

  • Transcribe audio from files or streams into text using z-ai-web-dev-sdk backend.
  • Support base64-encoded audio, enabling easy integration with web and server apps.
  • Use cases include meeting transcription, interview processing, podcast transcription, and accessibility.

Quick Start

Run the asr.ts script with your audio file path to obtain a transcription.

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe audio files into text using a backend script?

To transcribe audio files into text, you can run the provided TypeScript script with your audio file path to process the recording and output a plain text transcription using the z-ai-web-dev-sdk backend.

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

Yes, you can use base64-encoded audio for speech-to-text processing. The system explicitly supports base64 encoded audio inputs, enabling easy integration with web and server applications.

What are common use cases for converting speech to text?

Common use cases for converting speech to text include generating searchable meeting transcriptions, processing interviews, transcribing podcasts, and creating accessibility text from recorded audio streams.

Does this speech-to-text script support transcribing live audio streams?

The speech-to-text script supports audio analysis across files, recordings, and streams. It processes spoken audio through the z-ai-web-dev-sdk backend to output plain text transcriptions.

What do I need to set up before running the audio transcription script?

Before running the audio transcription script, you need the z-ai-web-dev-sdk dependency installed in your environment and an accessible audio file path or base64-encoded audio string ready for processing.