← Back to Skills Marketplace
277
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install voice-clone-tts-pro
Description
支持多引擎语音合成与声音克隆，可调节语速音调和情感，提供多语言多声音风格的自然语音输出。
Usage Guidance
这个技能看起来实现了它声称的功能，但有两点你应当注意：
1) 注册表条目没有列出任何必需的环境变量，但 SKILL.md 与代码会使用 OPENAI_API_KEY 和 ELEVENLABS_API_KEY（当你选择对应引擎时）。在提供任何 API 密钥之前，确认你信任此技能来源或只使用受限/测试密钥。
2) 技能会在你的主目录下写入缓存目录 (~/.cache/voice-clone/) 并可能调用系统命令（xdg-open）来尝试播放文件；如果你在受限环境或不希望写磁盘，请注意。
建议：在安装/运行前先在隔离环境（容器或虚拟机）中运行并审阅 voice-clone.py；仅为必要服务提供最小权限的 API 密钥；如果你无法确认作者或来源可疑，优先使用只靠本地模型（如 Coqui）的模式或寻找来源明确、有主页与源码审计记录的替代实现。
Capability Analysis
Type: OpenClaw Skill
Name: voice-clone-tts-pro
Version: 1.0.0
The skill provides legitimate text-to-speech and voice cloning functionality; however, it contains a shell injection vulnerability in voice-clone.py. The script uses os.system to execute xdg-open on the output file path without sanitization, which could allow arbitrary command execution if a malicious output path is provided. While this appears to be a coding flaw rather than intentional malice, it represents a significant security risk.
Capability Assessment
Purpose & Capability
技能名称、说明、SKILL.md 与包含的 Python 脚本在目的上是一致的：提供多引擎 TTS 与声音克隆（Edge TTS、OpenAI、ElevenLabs、Coqui）。依赖库（edge-tts、openai、elevenlabs、TTS 等）与功能相符。
Instruction Scope
SKILL.md 和 voice-clone.py 指示/使用了环境变量（OPENAI_API_KEY、ELEVENLABS_API_KEY）以及写入 ~/.cache/voice-clone/ 的文件；但注册元数据未将这些 env vars 列为必需。指令要求安装网络库并调用外部 API；没有发现脚本读取与任务无关的敏感本地路径或发送数据到未声明的自定义端点。
Install Mechanism
这是一个指令 + 脚本（无 install spec），推荐通过 pip 安装公开的 Python 包（edge-tts、openai、elevenlabs、TTS 等）。没有可疑的远程二进制下载或未知 URL。
Credentials
运行时确实需要第三方服务的 API 密钥（OpenAI、ElevenLabs），这些对于相应引擎是合理且必要的；但 registry metadata 未声明任何 required env vars，造成不一致。用户应该只提供最小权限/受限的 API 密钥并确认密钥用途。
Persistence & Privilege
技能不会要求 always:true 或修改其它技能/系统配置。唯一的持久性表现是创建并写入 ~/.cache/voice-clone/ 以保存输出音频（这是合理且可预期的）。
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-clone-tts-pro - After installation, invoke the skill by name or use
/voice-clone-tts-pro - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of voice-clone-tts-pro.
- Supports multi-engine TTS: Edge, OpenAI, ElevenLabs, and Coqui.
- Provides voice cloning and custom voice parameter adjustment.
- Allows users to specify voice, language, speed, pitch, and emotional tone.
- Includes example commands and supports batch processing.
- Audio output is saved locally; API keys required for some features.
- Preset and customizable voice options for both Chinese and English.
Metadata
Frequently Asked Questions
What is Voice Clone?
支持多引擎语音合成与声音克隆，可调节语速音调和情感，提供多语言多声音风格的自然语音输出。 It is an AI Agent Skill for Claude Code / OpenClaw, with 277 downloads so far.
How do I install Voice Clone?
Run "/install voice-clone-tts-pro" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice Clone free?
Yes, Voice Clone is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Voice Clone support?
Voice Clone is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Voice Clone?
It is built and maintained by SxLiuYu (@sxliuyu); the current version is v1.0.0.
More Skills