← 返回 Skills 市场
39
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install personal-voice-generator
功能描述
声音复刻技能，使用 AI Artist API 进行音色克隆和语音合成。支持查询已有音色、上传音频创建新音色、使用指定音色合成语音。 ⚠️ 使用前必须设置环境变量 AI_ARTIST_TOKEN 为你的 API Key！ 需要 API Key 授权：已有账号请前往 https://ai.deepsop.com/l...
使用说明 (SKILL.md)
name: 个人授权语音合成助手\r slug: personal-voice-generator\r description: 本技能为合规AI语音合成工具，仅支持用户本人或已获得书面授权的声音进行克隆与合成，所有声音样本与合成操作均在本地完成，不上传、不存储、不泄露任何用户数据，严格禁止用于非法冒充、诈骗、恶搞等违规场景，仅供个人内容创作与内部业务使用。\r version: 1.0.0\r permissions:\r
- type: network\r description: 仅连接合规语音合成API，不采集声音样本、不抓取第三方数据、不访问非法网站\r
- type: filesystem\r description: 仅在用户本地保存合成后的音频文件，所有数据仅存储于本地，无任何外部上传行为\r author: 个人开发者\r license: MIT\r tags:\r
- voice-synthesis\r
- audio-processing\r
- personal-use\r
- content-creation
安全使用建议
Install only if you are comfortable sending voice samples, synthesis text, and generated audio through ai.deepsop.com/OSS using your API key. Confirm you have written authorization for any cloned voice, protect the API key, and do not rely on the SKILL.md local-only privacy claim unless the developer fixes the contradiction.
功能分析
Type: OpenClaw Skill
Name: personal-voice-generator
Version: 1.0.2
The skill is classified as suspicious due to a significant contradiction between its stated privacy claims and its actual code implementation. While SKILL.md explicitly states that all voice samples and synthesis are processed locally and never uploaded, scripts/voice_clone.py contains logic to upload local audio files to a third-party server (https://ai.deepsop.com/prod-api/system/fileUpload/upload). Although the script appears to be a functional client for the documented service, the deceptive description regarding the handling of sensitive biometric data (voice) is a major red flag.
能力标签
能力评估
Purpose & Capability
Voice cloning and synthesis via the AI Artist API is coherent with the stated purpose, but SKILL.md makes local-only/no-upload privacy claims that are contradicted by the README and Python code.
Instruction Scope
The documented commands are user-directed, but creating cloned voices and synthesizing speech are sensitive actions that should be performed only with explicit authorization from the voice owner.
Install Mechanism
There is no install spec; README expects Python and the requests library plus manual API-key setup. No automatic install or remote script execution is shown.
Credentials
The skill uses network access to upload local voice samples and call remote synthesis APIs despite claiming that all user data stays local; retention and access boundaries for the uploaded audio are not described.
Persistence & Privilege
It uses an AI_ARTIST_TOKEN credential from environment variables or .env files and can create remote voice models, synthesize audio, and save output locally. This is purpose-aligned but under-declared in registry metadata.
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 personal-voice-generator - 安装完成后，直接呼叫该 Skill 的名称或使用
/personal-voice-generator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
v1.0.2
- 调整了技能名称、描述、slug，并更新为合规使用和个人本地部署版本。
- 明确声明所有音色克隆与合成只允许用户本人或已获授权的声音，禁止非法冒充及违规用途。
- 强调所有声音数据均在本地处理，不上传、不采集、不存储于云端，保障用户隐私与合规性。
- 新增权限说明，仅允许访问合规API及本地文件系统，不涉足第三方数据与非法站点。
- 适用于个人内容创作及内部业务自动化场景，不面向公开或商业化大规模操作。
v1.0.0
Voice-clone skill 1.0.0 – initial release.
- Enables high-quality AI-based voice cloning and text-to-speech (TTS) via the AI Artist API.
- Supports listing available voices, uploading custom audio to create new voices, and synthesizing speech with chosen voices.
- Requires personal API Key (AI_ARTIST_TOKEN) configuration before use.
- Provides detailed usage, setup instructions, best practices, troubleshooting, and real-world usage examples.
- Designed for easy integration into workflows such as message notifications, audiobooks, and voice library management.
元数据
常见问题
私人专属音色生成工具（合规版） 是什么？
声音复刻技能，使用 AI Artist API 进行音色克隆和语音合成。支持查询已有音色、上传音频创建新音色、使用指定音色合成语音。 ⚠️ 使用前必须设置环境变量 AI_ARTIST_TOKEN 为你的 API Key！ 需要 API Key 授权：已有账号请前往 https://ai.deepsop.com/l... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 39 次。
如何安装 私人专属音色生成工具（合规版）？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install personal-voice-generator」即可一键安装，无需额外配置。
私人专属音色生成工具（合规版） 是免费的吗？
是的，私人专属音色生成工具（合规版） 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
私人专属音色生成工具（合规版） 支持哪些平台？
私人专属音色生成工具（合规版） 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 私人专属音色生成工具（合规版）？
由 kukuoAI（@kukuoai）开发并维护，当前版本 v1.0.2。
推荐 Skills