← Back to Skills Marketplace
463
Downloads
0
Stars
4
Active Installs
3
Versions
Install in OpenClaw
/install voice-clone
Description
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...
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
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.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-clone - After installation, invoke the skill by name or use
/voice-clone - Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Frequently Asked Questions
What is Voice Clone?
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... It is an AI Agent Skill for Claude Code / OpenClaw, with 463 downloads so far.
How do I install Voice Clone?
Run "/install voice-clone" 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 scikkk (@scikkk); the current version is v1.0.2.
More Skills