ASR

Transcribe audio files to text using the z-ai-web-dev-sdk.

26|15|Updated Dec 25, 2025
One-click install
npx skills add https://github.com/AnswerZhao/agent-skills --skill asr-answerzhao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/AnswerZhao/agent-skills/tree/main/glm-skills/ASR
Command: npx skills add https://github.com/AnswerZhao/agent-skills --skill asr-answerzhao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables automatic speech-to-text transcription from audio inputs using the z-ai-web-dev-sdk.

Core Features & Use Cases

  • High-accuracy transcription: Converts spoken language from audio files into text with reliable results.
  • Backend-first processing: Designed to run in server environments using the z-ai-web-dev-sdk.
  • Use Case: Transcribe meetings, interviews, podcasts, or voice memos for searchable records and analytics.

Quick Start

Run the example by pointing the script at your audio file.

  • ts-node scripts/asr.ts ./your-audio.wav
  • Alternatively, compile to JS and run: node dist/asr.js ./your-audio.wav

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 to text in a Node.js backend?

To transcribe audio to text in a backend, you can use this Skill with the z-ai-web-dev-sdk to process audio file inputs. It runs as a server-side script, converting spoken language from your audio files into accurate text.

Can I use this for real-time speech-to-text transcription of meetings?

Yes, this speech-to-text Skill supports both real-time and batch transcription scenarios for meetings, interviews, and podcasts. It processes audio inputs in backend environments to generate searchable text records.

Do I need the z-ai-web-dev-sdk dependency to run the audio transcription script?

Yes, you must install the z-ai-web-dev-sdk dependency to perform speech-to-text transcription. The Skill relies on this SDK to execute its backend scripts and accurately convert your audio inputs into text.

What's the best way to execute the speech-to-text script for an audio file?

The best way to execute the speech-to-text script is by running it via ts-node pointing to your audio file, such as `ts-node scripts/asr.ts ./your-audio.wav`. Alternatively, compile the script to JavaScript and run it with Node.js.

Does this automatic speech recognition Skill process audio files on the server or client?

This automatic speech recognition Skill processes audio files on the server. It is designed as a backend-first solution, running in server environments using the z-ai-web-dev-sdk to handle transcription tasks.

What audio formats are supported for batch transcription in backend environments?

The Skill handles batch transcription in backend environments by processing audio inputs through the z-ai-web-dev-sdk. You can point the script at your audio file, such as a WAV file, to generate accurate text transcripts.