Saltar al contenido
TakoAPI
Volver a skills

zhipu-asr

por franklu0819-lang

AI & LLMs
476Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

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

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

Transcribed Chinese text with improved recognition of specified names

Requisitos

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

Instalación

clawhub install franklu0819-lang/zhipu-asr

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces