← Back to Skills Marketplace
867
Downloads
1
Stars
6
Active Installs
1
Versions
Install in OpenClaw
/install zhipu-tts
Description
Text-to-speech conversion using Zhipu AI (BigModel) GLM-TTS model. Use when you need to convert text to audio files with various voice options. Supports Chin...
Usage Guidance
This skill is coherent and appears to do what it says: convert supplied Chinese text to audio via Zhipu AI. Before installing, confirm you trust the Zhipu/bigmodel service (text you send will be transmitted to that third-party). Protect your ZHIPU_API_KEY (don't embed it in shared scripts). Ensure jq and curl are available. Be aware the script prints the input text to stderr (could appear in logs); avoid sending sensitive secrets or PII to the TTS API. If you need higher assurance, inspect the script locally and test with non-sensitive text first.
Capability Analysis
Type: OpenClaw Skill
Name: zhipu-tts
Version: 1.0.0
The OpenClaw skill bundle for Zhipu AI Text-to-Speech is classified as benign. The `scripts/text_to_speech.sh` script correctly handles user-provided input by using `jq --arg` for JSON payload construction, which safely escapes text, and consistently quotes all variables (`"$VAR"`) when passed to shell commands like `curl`, `file`, and `ls`. This prevents shell injection vulnerabilities. The `ZHIPU_API_KEY` is securely read from environment variables and sent only to the legitimate Zhipu AI API endpoint, with no evidence of data exfiltration or other malicious activities. The `SKILL.md` and `README.md` files contain only descriptive instructions without any prompt injection attempts.
Capability Assessment
Purpose & Capability
Name/description match the actual behavior: script sends provided Chinese text to Zhipu's GLM-TTS endpoint and saves audio. Required env var (ZHIPU_API_KEY) and jq are appropriate for this purpose; nothing else requested that is unrelated.
Instruction Scope
SKILL.md and the shell script limit actions to building a JSON payload, POSTing it to the documented API, and saving the resulting audio file. The script reads only the provided text and ZHIPU_API_KEY; it does not attempt to read unrelated files or other environment variables. Note: the script prints the input text to stderr (may appear in logs).
Install Mechanism
No install spec (instruction-only plus a helper script) — lowest risk. The script uses curl and common utilities (file, ls) but only jq is declared as required; make sure curl is available in your environment.
Credentials
Only a single service-specific secret (ZHIPU_API_KEY) is required, which is proportionate for a remote TTS API. The skill does not request unrelated credentials or config paths.
Persistence & Privilege
Skill does not request permanent/always presence and does not modify system or other skills' configuration. Autonomous invocation is allowed by platform default, but the skill itself is not highly privileged.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install zhipu-tts - After installation, invoke the skill by name or use
/zhipu-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Text-to-speech conversion using Zhipu AI GLM-TTS model with 7 voice personas, speed control, and multiple output formats
Metadata
Frequently Asked Questions
What is Zhipu AI TTS?
Text-to-speech conversion using Zhipu AI (BigModel) GLM-TTS model. Use when you need to convert text to audio files with various voice options. Supports Chin... It is an AI Agent Skill for Claude Code / OpenClaw, with 867 downloads so far.
How do I install Zhipu AI TTS?
Run "/install zhipu-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Zhipu AI TTS free?
Yes, Zhipu AI TTS is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Zhipu AI TTS support?
Zhipu AI TTS is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Zhipu AI TTS?
It is built and maintained by xiaofei (@franklu0819-lang); the current version is v1.0.0.
More Skills