ASR

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

Updated Jan 13, 2026
One-click install
npx skills add https://github.com/zeustriton/radarDigital_QA --skill asr-zeustriton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/zeustriton/radarDigital_QA/tree/main/skills/ASR
Command: npx skills add https://github.com/zeustriton/radarDigital_QA --skill asr-zeustriton

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Speech-to-text transcription enables apps to convert spoken language in audio files into searchable, editable text, increasing accessibility and automation.

Core Features & Use Cases

  • Backend-ready: Transcribe audio securely on the server using the z-ai-web-dev-sdk.
  • Flexible input: Transcribe from local files or base64-encoded audio streams, with support for common formats.
  • Use cases: Meeting transcripts, interviews, podcasts, captions, and accessibility features for content.

Quick Start

Transcribe a local audio file using the CLI: z-ai asr --file ./audio.wav -o transcript.json. For SDK usage, see the included example in skills/ASR/scripts/asr.ts which reads an audio file, encodes to base64, and calls the ASR API.

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 from an audio file on the backend?

To transcribe speech to text on the backend, this Skill reads local audio files, encodes them to base64, and calls the ASR API via the z-ai-web-dev-sdk to return a plain text transcription.

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

Yes, you can use base64-encoded audio streams for speech-to-text transcription, as the Skill explicitly supports processing base64-encoded audio inputs alongside local files to generate transcripts.

Does the z-ai-web-dev-sdk support transcribing podcasts and meeting audio?

Yes, the z-ai-web-dev-sdk supports transcribing meeting transcripts, interviews, and podcasts by converting spoken language in audio files into searchable, editable plain text.

What is the best way to automate voice-enabled app transcription?

The best way to automate voice-enabled app transcription is using this backend Skill with the z-ai-web-dev-sdk, which securely processes audio files and returns plain text for accessibility and automation.

How do I run speech-to-text transcription using a CLI command?

You can run speech-to-text transcription using the CLI command: z-ai asr --file ./audio.wav -o transcript.json, which processes the local audio file and outputs the transcription to a JSON file.