Setup & Installation
openclaw skills install @franklu0819-lang/zhipu-tts
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install zhipu-tts
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
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: convert '欢迎使用智能语音服务' to speech with xiaochen voice at 1.2x speed
AGENT
- 1Set ZHIPU_API_KEY in environment
- 2Run bash scripts/text_to_speech.sh with text, voice, speed, format, and output filename arguments
- 3Script calls Zhipu AI GLM-TTS API with the provided parameters
- 4API returns audio data, script writes it to the specified WAV file
OUTPUT
greeting.wav audio file with xiaochen voice at 1.2x speed
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
ZHIPU_API_KEY environment variable from bigmodel.cn