← 返回 Skills 市场
463
总下载
0
收藏
4
当前安装
3
版本数
在 OpenClaw 中安装
/install voice-clone
功能描述
Guide users through SenseAudio platform voice cloning, then generate TTS with cloned `voice_id` values. Use when users want to clone voices, manage cloned vo...
安全使用建议
This skill appears coherent and only needs your SenseAudio API key plus Python packages to validate audio locally and call the SenseAudio TTS endpoint. Before installing: ensure the API key you provide is scoped appropriately (use a least-privilege/rotatable key if the platform supports it), verify you trust https://senseaudio.cn and its privacy policy for handling uploaded audio, and be aware the agent will make network calls to the SenseAudio API and may transmit voice_id and input text. The pydub dependency is optional for local audio checks. If you have high-sensitivity audio, consider reviewing SenseAudio’s retention/usage policies before uploading or using cloned voices.
功能分析
Type: OpenClaw Skill
Name: voice-clone
Version: 1.0.2
The skill provides legitimate integration with the SenseAudio platform for voice cloning and TTS generation. It uses standard Python libraries (requests, pydub) to interact with the official API endpoint (api.senseaudio.cn) and includes helper functions for audio validation and synthesis that align with its stated purpose. No malicious patterns, such as data exfiltration or unauthorized command execution, were detected in SKILL.md or the provided code snippets.
能力评估
Purpose & Capability
Name/description (SenseAudio voice cloning + TTS) match the declared requirements: python3, requests, pydub, and a single SENSEAUDIO_API_KEY. None of the required binaries or env vars are unrelated to the stated functionality.
Instruction Scope
SKILL.md stays within scope: it guides users to perform platform-side cloning, validates audio locally (optional), and shows POST calls to the official SenseAudio TTS endpoint using the API key in an Authorization header. It does not instruct reading unrelated system files or exfiltrating secrets; it even warns not to log API keys.
Install Mechanism
Install spec lists Python packages (requests, pydub) only. These are standard PyPI libraries and are proportionate to the task (HTTP calls and optional local audio handling). No arbitrary downloads or custom binaries are requested.
Credentials
Only SENSEAUDIO_API_KEY is required and is declared as the primary credential; that is appropriate for a skill that calls SenseAudio APIs. No unrelated secrets or multiple credential requirements are present.
Persistence & Privilege
always is false (no forced inclusion). The skill does not request system-wide changes or access to other skills' configs. Autonomous invocation is allowed by default but is not combined with elevated privileges here.
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 voice-clone - 安装完成后，直接呼叫该 Skill 的名称或使用
/voice-clone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
No user-facing or functional changes in this version.
- No file changes were detected for version 1.0.2.
- Documentation, behavior, and supported features remain unchanged from previous versions.
v1.0.1
- Clarified that all voice cloning is done on the SenseAudio platform, not via public API.
- Now guides users through the official platform side workflow and enforces sample requirements for cloning (duration, format, quality).
- API integration now only uses `SENSEAUDIO_API_KEY` (not `API_KEY`) for authentication.
- Provides concise Python helpers for TTS generation, including support for polyphonic dictionary control with cloned voices.
- Specifies that only TTS from an existing cloned `voice_id` is supported; explains slot management and source audio validation.
- Updated dependency instructions: requires `python3`, `requests`, and optionally `pydub` for local audio checks.
v1.0.0
Initial release of SenseAudio Voice Cloner.
- Clone voices from 3–30 second audio samples to create custom voice models.
- Generate audio content using cloned voices with emotion and style control.
- Supports management of voice slots and a voice library.
- Includes guidance for voice cloning on the platform, API usage examples, and batch generation.
- Provides advanced features like polyphone control, emotion presets, and audio quality validation.
元数据
常见问题
Voice Clone 是什么？
Guide users through SenseAudio platform voice cloning, then generate TTS with cloned `voice_id` values. Use when users want to clone voices, manage cloned vo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 463 次。
如何安装 Voice Clone？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install voice-clone」即可一键安装，无需额外配置。
Voice Clone 是免费的吗？
是的，Voice Clone 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Voice Clone 支持哪些平台？
Voice Clone 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 Voice Clone？
由 scikkk（@scikkk）开发并维护，当前版本 v1.0.2。
推荐 Skills