Voice Clone TTS
v1.0.0声纹克隆和语音合成。上传音频样本克隆声纹，用克隆声纹或预设声纹生成语音。支持多个后端：MiniMax、ElevenLabs、Fish Audio、Azure TTS、OpenAI TTS。支持情绪控制、语速调整、批量生成。触发词：语音合成、TTS、声纹克隆、voice clone、text to speech、配...
⭐ 0· 155·0 current·0 all-time
byOlivia_Pp@oliviapp8
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description match the content: the SKILL.md describes voice cloning and TTS and lists concrete backends (MiniMax, ElevenLabs, Fish Audio, Azure, OpenAI). The skill does not request unrelated binaries or environment variables; backend-setup explains the API keys that will be needed by those providers, which is expected for this capability.
Instruction Scope
Instructions stay within TTS/voice cloning scope (upload audio samples, call provider APIs, return voice_id/audio files). They do not instruct reading arbitrary system files or unrelated credentials. Important caveat: the workflow explicitly sends user audio samples to external services — this is necessary for cloning but raises privacy/consent concerns and depends on third‑party data retention/policy.
Install Mechanism
Instruction-only skill with no install spec or code files; nothing is written to disk or auto-installed by the skill itself, which minimizes supply‑chain risk.
Credentials
The skill does not declare required env vars, but the referenced backend-setup clearly requires provider API keys (Minimax/ElevenLabs/Fish/Azure/OpenAI). Those credentials are proportional to the stated purpose. Because the skill is instruction-only, it relies on the agent/user to supply/configure keys; ensure keys are provided only for intended backends and stored securely.
Persistence & Privilege
always:false and no install means the skill does not request permanent/surprising system presence or modify other skills/config. Agent autonomous invocation is allowed (platform default) but not combined with any additional privileged behavior here.
Assessment
This skill appears coherent for voice cloning and TTS and will require you to supply API keys for one or more third‑party providers (Minimax, ElevenLabs, Fish Audio, Azure, OpenAI). Before installing or using it: (1) only upload voice samples you own or have explicit consent to use; cloning someone else's voice can be illegal or violate platform policies; (2) review each provider's data retention and privacy policies — uploading samples sends sensitive biometric data off your device; (3) store provider API keys securely and only grant the minimum scope needed; (4) prefer built‑in platform cloning features when available (the SKILL.md itself recommends that); (5) if you need stronger assurance, ask the skill author where and how API keys/config are stored and whether the agent will log or transmit additional context. The absence of code and install steps lowers supply‑chain risk, but the core privacy/ethical risks of voice cloning remain and should guide your decision.Like a lobster shell, security has layers — review code before you run it.
latestvk970qvaef572fqknafj3nbpyn983d77y
License
MIT-0
Free to use, modify, and redistribute. No attribution required.