ASR

Transcribe spoken audio from files or base64 inputs into text.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/TIAN0517/iosboss --skill asr-tian0517
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/TIAN0517/iosboss/tree/main/temp_extract/99999999/skills/ASR
Command: npx skills add https://github.com/TIAN0517/iosboss --skill asr-tian0517

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables applications to convert spoken language in audio into written text, facilitating transcripts, voice interfaces, and searchable records.

Core Features & Use Cases

  • Base64 input support: Transcribe audio provided as base64 data.
  • File-based transcription: Transcribe WAV/MP3 audio files via backend services.
  • Batch processing & automation: Transcribe multiple files or streams for meetings, interviews, and podcasts.
  • Use Case: Convert recorded meetings or interviews into editable transcripts for minutes and analysis.

Quick Start

Transcribe a local audio file using the CLI: z-ai asr --file ./meeting.wav -o transcript.json

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe an audio file to text in a backend environment?

To transcribe audio to text in a backend environment, you can use a speech-to-text SDK to process file-based audio inputs like WAV or MP3 and return a written text transcription.

Can I transcribe base64-encoded audio data without a local file?

Yes, speech-to-text transcription can process base64-encoded audio data directly, allowing you to transcribe audio streams without needing a local file-based input.

What is the best way to convert recorded meetings into editable transcripts?

The best way to convert recorded meetings into editable transcripts is using batch speech-to-text processing, which transcribes multiple audio files into text for minutes and analysis.

Does speech-to-text transcription work with WAV and MP3 audio formats?

Yes, backend speech-to-text transcription supports common audio formats including WAV and MP3, processing them via file-based inputs to generate text transcriptions.

Do I need a specific SDK to run audio transcription tasks?

Yes, you need a backend environment with the z-ai-web-dev-sdk installed to transcribe spoken audio into written text and access the required speech-to-text processing logic.

Can I automate batch processing for podcast audio transcriptions?

Yes, you can automate batch processing for podcast audio transcriptions by transcribing multiple files or streams within a backend service to produce searchable text records.