← 返回 Skills 市场
632
总下载
3
收藏
2
当前安装
4
版本数
在 OpenClaw 中安装
/install zai-tts
功能描述
Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output w...
安全使用建议
This skill is coherent for using audio.z.ai via the uvx CLI, but be careful with the auth token. The SKILL.md asks you to copy a token from browser localStorage — treat that token like a password: don't paste it into public places, prefer creating a scoped API key if the service provides one, and store it in a secure credential store rather than a plain environment file if possible. Before installing, verify the source of the 'uv' package (brew/pypi) to ensure you're installing the intended uvx client. If you are uncomfortable extracting session tokens from your browser, contact the service to get an official API token or use an alternative TTS provider with clearer API key support.
功能分析
Type: OpenClaw Skill
Name: zai-tts
Version: 1.0.3
The skill is a legitimate text-to-speech integration for the GLM-TTS service (audio.z.ai). It uses the standard `uvx` tool to execute the `zai-tts` Python package and requires the user to provide their own credentials via environment variables. The instructions in SKILL.md are consistent with the stated functionality, and no evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description (GLM-TTS via uvx) match the declared requirements: uvx binary and ZAI_AUDIO_USERID / ZAI_AUDIO_TOKEN environment variables are exactly what a CLI client to audio.z.ai would need.
Instruction Scope
SKILL.md only instructs running the uvx CLI with arguments and how to obtain credentials. It explicitly tells users to extract auth info from browser localStorage (JSON.parse(localStorage['auth-storage']).state.token), which is sensitive but directly related to authenticating to audio.z.ai; the instructions do not attempt to read other system files or unrelated credentials.
Install Mechanism
Install spec uses common package managers (brew or pip) for a package named 'uv' that provides uvx. Having both brew and pip installers is redundant but not inherently risky; no arbitrary download URLs or extracted archives are present.
Credentials
Only two env vars (userId and token) are required, and the token is the primary credential — appropriate for a remote TTS service. However the recommended method to obtain them (copying a session token from localStorage) can encourage insecure handling of session tokens and may expose long-lived credentials if not managed carefully.
Persistence & Privilege
Skill does not request always:true, does not declare config paths, and does not modify other skills; autonomous invocation is default but not excessive for this type of integration.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install zai-tts - 安装完成后，直接呼叫该 Skill 的名称或使用
/zai-tts触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.3
- Added skill homepage link for easier access to documentation.
- Usage section now shows support for inputting text from files with the `-f` option.
v1.0.2
- Changed audio output file extension in usage examples from .mp3 to .wav.
- Updated all relevant command examples to use .wav for generated audio files.
- No functional or code changes; documentation update only.
v1.0.1
- The ZAI_AUDIO_TOKEN environment variable is now marked as secret in installation metadata.
v1.0.0
- Initial release of zai-tts skill for text-to-speech conversion using the GLM-TTS service.
- Provides the `uvx zai-tts` command to generate audio from text with customizable speed, volume, and voice selection.
- Requires configuration of `ZAI_AUDIO_USERID` and `ZAI_AUDIO_TOKEN` from audio.z.ai.
- Supports multiple pre-cloned voices and ability to list available voices.
- Offers clear instructions for installation and environment setup.
元数据
常见问题
🗣️ Text-to-speech using GLM-TTS for generating audio 是什么？
Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output w... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 632 次。
如何安装 🗣️ Text-to-speech using GLM-TTS for generating audio？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install zai-tts」即可一键安装，无需额外配置。
🗣️ Text-to-speech using GLM-TTS for generating audio 是免费的吗？
是的，🗣️ Text-to-speech using GLM-TTS for generating audio 完全免费（开源免费），可自由下载、安装和使用。
🗣️ Text-to-speech using GLM-TTS for generating audio 支持哪些平台？
🗣️ Text-to-speech using GLM-TTS for generating audio 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 🗣️ Text-to-speech using GLM-TTS for generating audio？
由 Alone（@al-one）开发并维护，当前版本 v1.0.3。
推荐 Skills