ASR

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

Updated Jan 7, 2026
One-click install
npx skills add https://github.com/ashishkushwaha-mpu/ChocoWrap --skill asr-ashishkushwaha-mpu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/ashishkushwaha-mpu/ChocoWrap/tree/main/skills/ASR
Command: npx skills add https://github.com/ashishkushwaha-mpu/ChocoWrap --skill asr-ashishkushwaha-mpu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables developers to convert spoken language in audio into written text by leveraging the z-ai-web-dev-sdk, enabling voice-driven apps, transcripts, and accessibility features.

Core Features & Use Cases

  • Backend transcription: transcribe base64-encoded audio using the z-ai-web-dev-sdk in server-side code.
  • Versatile usage: supports file-based, base64, and streaming transcription for meetings, interviews, podcasts, and voice memos.
  • Practical scenarios: create searchable transcripts for meetings, captions for podcasts, and accessibility aids for content.

Quick Start

  • Transcribe an audio file via CLI: z-ai asr --file ./audio.wav
  • Transcribe from base64 input: z-ai asr --base64 "BASE64_DATA" -o transcript.json
  • Stream transcription: z-ai asr -f ./audio.wav --stream

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe base64-encoded audio to text in a backend environment?

To transcribe base64-encoded audio to text, you can use the z-ai-web-dev-sdk in your server-side code. The ASR Skill processes the base64 audio input and returns structured transcription text for backend workflows.

Does the z-ai-web-dev-sdk support streaming speech-to-text for podcasts?

Yes, the z-ai-web-dev-sdk supports streaming speech-to-text transcription. You can stream audio files directly to generate real-time transcripts for podcasts, meetings, and voice memos.

Can I use this ASR Skill to generate accessibility captions from voice notes?

You can use this ASR Skill to generate accessibility captions from voice notes. It converts spoken language into written text, supporting common audio formats for accessibility workflows.

What is the best way to convert a local audio file into a searchable meeting transcript?

The best way to convert a local audio file into a searchable meeting transcript is by passing the file to the ASR Skill. It uses the z-ai-web-dev-sdk to process the audio and output structured text.

Do I need the z-ai-web-dev-sdk installed to perform backend audio transcription?

Yes, you need the z-ai-web-dev-sdk installed to perform backend audio transcription. This Skill implements backend-only SDK usage to process base64 audio and return transcription text.