ASR

Transcribe base64-encoded audio into text using the z-ai-web-dev-sdk.

Updated Jan 8, 2026
One-click install
npx skills add https://github.com/chancoute/sgin --skill asr-chancoute
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/chancoute/sgin/tree/main/skills/ASR
Command: npx skills add https://github.com/chancoute/sgin --skill asr-chancoute

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables turning spoken audio into accurate text transcripts for searchable archives, voice-enabled interfaces, and accessibility applications.

Core Features & Use Cases

  • ASR via z-ai-web-dev-sdk: Backend transcription using base64-encoded audio inputs.
  • Base64 Input Support: Accepts base64 audio streams and transcribes them on the server.
  • CLI & SDK Examples: Provides example usage through CLI and programmatic SDK calls for production workflows.

Quick Start

Install the z-ai-web-dev-sdk, place an audio file, and run a transcription workflow using the provided scripts or CLI commands.

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe speech to text using Node.js?

Base64 audio encoding is required for speech-to-text transcription with this backend SDK because it safely transmits binary audio data as text streams to the asr.create API for processing.

Can I use the z-ai-web-dev-sdk for backend audio transcription?

You need a Node.js backend environment and the z-ai-web-dev-sdk installed to run the transcription workflows, read audio files, and execute the asr.create API calls for speech-to-text conversion.

How do I convert an audio file to base64 for transcription?

Convert an audio file to base64 for transcription by reading its binary data within your Node.js backend environment and passing the resulting base64 string to the asr.create API.

What is the best way to handle speech-to-text transcription errors in Node.js?

The best way to handle speech-to-text transcription errors in Node.js is to implement proper error handling logic around your asr.create API calls when processing base64 audio streams.