zhipu-tts
by franklu0819-lang
Git & GitHubBrief
Text-to-speech conversion using Zhipu AI (BigModel) GLM-TTS model.
Description
What This Skill Does
Converts Chinese text to speech using Zhipu AI's GLM-TTS model. Supports seven voice personas, speed control from 0.5x to 2x, and WAV or PCM output. Input is limited to 1024 characters per request.
Provides native Chinese voice synthesis with multiple distinct personas through a simple bash script, without requiring any audio SDK or programming beyond a shell.
When to Use It
- Generate customer service greeting audio files
- Create narration for Chinese video content
- Produce character voices for entertainment projects
- Convert Chinese app UI text to audio for accessibility
- Generate announcement audio for events or broadcasts
Example Workflow
User asks: convert '欢迎使用智能语音服务' to speech with xiaochen voice at 1.2x speed
- 1
Set ZHIPU_API_KEY in environment
- 2
Run bash scripts/text_to_speech.sh with text, voice, speed, format, and output filename arguments
- 3
Script calls Zhipu AI GLM-TTS API with the provided parameters
- 4
API returns audio data, script writes it to the specified WAV file
greeting.wav audio file with xiaochen voice at 1.2x speed
Requirements
- ZHIPU_API_KEY environment variable from bigmodel.cn
Installation
clawhub install franklu0819-lang/zhipu-ttsRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.