skills.rest
favouritehu
favouritehuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ASR

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

Updated Aug 23, 2026
Search Tags:#backend#CLI#speech-to-text#transcribe#base64#ASR#z-ai-web-dev-sdk
One-click install
npx skills add https://github.com/favouritehu/call_tracking --skill asr-favouritehu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ASR
Source: https://github.com/favouritehu/call_tracking/tree/main/skills/ASR
Command: npx skills add https://github.com/favouritehu/call_tracking --skill asr-favouritehu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribes audio into written text by leveraging the z-ai-web-dev-sdk, enabling developers to convert speech in recordings, voice notes, and meetings into searchable, editable text.

Core Features & Use Cases

  • Back-end transcription: Convert audio files to text efficiently for transcripts, captions, and indexing.
  • CLI and code integration: Use the provided CLI commands or SDK-based code samples to integrate ASR into apps and workflows.
  • Real-world scenarios: Transcribe interviews, meetings, or podcasts, or build voice-enabled features with base64-encoded audio input.

Quick Start

Use the ASR skill to transcribe an audio file with a single command or API call:

  • CLI: z-ai asr --file ./audio.wav
  • SDK: await (await ZAI.create()).audio.asr.create({ file_base64: base64Audio });

Frequently Asked Questions about ASR

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

FAQPage Schema
How do I transcribe audio to text using a backend SDK?▼

To transcribe audio to text on the backend, use the z-ai-web-dev-sdk to process recordings or voice notes. This skill provides CLI and code examples, accepting either file paths or base64-encoded audio to generate written text efficiently.

Can I use base64 audio input for speech-to-text processing?▼

Yes, base64 audio input is supported for speech-to-text processing. The SDK integration allows you to pass base64-encoded audio directly via code, enabling transcription of voice notes and recordings without needing a physical file path.

How do I transcribe an audio file from the command line?▼

You can transcribe an audio file from the command line using the provided CLI. Execute a command like `z-ai asr --file ./audio.wav` to convert your speech recordings into written text quickly.

Does the z-ai-web-dev-sdk support real-time speech transcription?▼

The z-ai-web-dev-sdk supports real-time scenarios for speech transcription alongside batch processing. It is designed for backend-only usage, allowing developers to transcribe meetings, interviews, and podcasts into searchable text.

What is the best way to generate text transcripts for meetings?▼

The best way to generate text transcripts for meetings is using backend ASR with the z-ai-web-dev-sdk. It efficiently converts audio from recordings or voice notes into searchable, editable text for indexing and captions.

Related Skills

Explore More Software Engineering Skills→
7126112171261121

ASR

Transcribe Base64 encoded audio files into text using the z-ai-web-dev-sdk.

Community
Intermediate
buda-aibuda-ai
25

speech-transcriber

Transcribe audio and video into timestamped TXT, SRT, and JSON transcripts.

Official
Advanced
Sspanwar31Sspanwar31
4

ASR

Transcribe base64-encoded audio into written text via CLI or SDK.

Community
Advanced
TikTzukiTikTzuki

Google Cloud Text-to-Speech

Convert text to speech and transcribe audio via cloud APIs.

Community
Advanced