← 返回 Skills 市场
334
总下载
1
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install voiceclone
功能描述
Voice cloning and TTS using MiniMax API. User must provide a voice name when cloning; after success, voice_name->voice_id is written back to this skill doc f...
安全使用建议
This skill appears to do exactly what it says: clone audio to MiniMax, create voices, synthesize speech, and update a mapping block in SKILL.md. Before installing/running: (1) ensure you set one of MINIMAX_API_KEY / MINIMAX_KEY / MINIMAX_GROUP_API_KEY (the registry metadata currently omits this requirement); (2) run the script from the skill directory (or confirm the SKILL.md path) to avoid unintended file writes; (3) inspect the included Python script if you want to be sure it accesses only the expected endpoints (it calls api.minimax.io); (4) only provide audio files and output paths you trust and avoid running with elevated privileges. If you want the registry listing fixed, ask the skill author to declare the required env var(s) in the registry metadata so it matches SKILL.md and the code.
功能分析
Type: OpenClaw Skill
Name: voiceclone
Version: 1.0.1
The skill provides voice cloning and TTS capabilities using the MiniMax API (api.minimax.io). A security vulnerability exists in `scripts/minimax_voice_clone_tts.py` within the `update_skill_registry` function, which implements a 'write-back' feature to persist voice mappings into `SKILL.md`. This function lacks input sanitization for the `display_name` and `voice_id` parameters, allowing for indirect prompt injection by inserting malicious markdown instructions into the skill's documentation. While the behavior is documented and aligned with the skill's stated purpose, the self-modifying nature of the instructions poses a high-risk surface for attacking the AI agent.
能力评估
Purpose & Capability
The skill name, description, SKILL.md instructions, and included Python script all align: they upload audio to MiniMax, create cloned voices, perform TTS, and maintain a mapping block in SKILL.md. However, registry metadata shown earlier lists no required environment variables/primary credential while both SKILL.md and the script require one of MINIMAX_API_KEY / MINIMAX_KEY / MINIMAX_GROUP_API_KEY. This is an inconsistency in the manifest (likely an author oversight) but the credentials themselves are appropriate for the stated purpose.
Instruction Scope
The SKILL.md and the script restrict actions to: reading a user-provided audio file, calling MiniMax endpoints, writing TTS output to the provided path, and reading/writing this skill's SKILL.md mapping block. There are no instructions to read unrelated system files or exfiltrate arbitrary data. The write-back of mappings to SKILL.md is explicit and documented (so users should expect it).
Install Mechanism
There is no registry install spec (instruction-only), and required dependency is only 'requests' per requirements.txt. That is low risk, but the presence of a runnable script plus a requirements.txt means users must install Python deps manually; there is no automated install step in the registry metadata. This is operationally inconvenient but not a security red flag.
Credentials
The script only requires a MiniMax API key (one of MINIMAX_API_KEY / MINIMAX_KEY / MINIMAX_GROUP_API_KEY) for API access — this is proportionate to voice cloning/TTS. The earlier registry summary incorrectly omitted these required env vars, which should be corrected so users know they must supply credentials before running.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It writes only to its own SKILL.md mapping block and to arbitrary output paths the user supplies (e.g., --output), which is expected for a TTS tool. Users should run it from the intended skill directory to avoid accidentally updating the wrong file.
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 voiceclone - 安装完成后，直接呼叫该 Skill 的名称或使用
/voiceclone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
v1.0.1
- Added requirements.txt with installation instructions for Python dependencies.
- Expanded SKILL.md with a clear "Install" section and explicit Python/runtime/dependency requirements.
- Documented required and optional environment variables for authentication in the SKILL.md frontmatter and table.
- Clarified the script’s scope, file read/write behavior, and API/network interactions.
- No changes to core logic—documentation and setup improvements only.
v1.0.0
Voice cloning and TTS using MiniMax API. User
元数据
常见问题
Mimimax Voice Clone +TTS 是什么？
Voice cloning and TTS using MiniMax API. User must provide a voice name when cloning; after success, voice_name->voice_id is written back to this skill doc f... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 334 次。
如何安装 Mimimax Voice Clone +TTS？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install voiceclone」即可一键安装，无需额外配置。
Mimimax Voice Clone +TTS 是免费的吗？
是的，Mimimax Voice Clone +TTS 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Mimimax Voice Clone +TTS 支持哪些平台？
Mimimax Voice Clone +TTS 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 Mimimax Voice Clone +TTS？
由 Tan（@socketnet）开发并维护，当前版本 v1.0.1。
推荐 Skills