Skip to content
TakoAPI
Back to skills

zhipu-asr

by franklu0819-lang

AI & LLMs
476Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Automatic Speech Recognition (ASR) using Zhipu AI (BigModel) GLM-ASR model.

Description

What This Skill Does

Transcribes Chinese audio files to text using Zhipu AI's GLM-ASR model. Accepts WAV, MP3, and several other formats, converting non-native formats via ffmpeg. Supports context prompts and custom hotwords to improve accuracy for specialized vocabulary.

The hotword and context prompt features give it an edge over generic ASR tools when transcribing content with proper names, technical terminology, or multi-segment recordings.

When to Use It

  • Transcribing recorded business meetings in Chinese
  • Converting lecture recordings to text for note-taking
  • Processing interview audio for documentation
  • Transcribing multi-part conversations with continuity context
  • Boosting accuracy for domain-specific terms like medical or legal jargon

Example Workflow

INPUT

User asks: transcribe meeting.wav with attendee names Zhang and Li

AGENT
  1. 1

    Check audio file format and size against 25MB/30s limits

  2. 2

    Convert format to WAV or MP3 if needed using ffmpeg

  3. 3

    Call speech_to_text.sh with the file and hotwords '张总,李经理'

  4. 4

    Send request to Zhipu AI GLM-ASR API with ZHIPU_API_KEY

  5. 5

    Parse JSON response and extract the 'text' field

OUTPUT

Transcribed Chinese text with improved recognition of specified names

Requirements

  • ZHIPU_API_KEY environment variable from bigmodel.cn
  • ffmpeg installed for non-WAV/MP3 format conversion

Installation

clawhub install franklu0819-lang/zhipu-asr

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links