ClawHub

Characteristic Voice

v0.1.1

Use this skill whenever the user wants speech to sound more human, companion-like, or emotionally expressive. Triggers include: any mention of 'say like', 't...

⭐ 1· 419·2 current·2 all-time
bykusuriuri@ksuriuri·duplicate of @ksuriuri/noizai-characteristic-voice (0.1.0)·canonical: @ksuriuri/noiz-characteristic-voice
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
ℹ
Purpose & Capability
The skill implements expressive TTS and optionally voice cloning via the Noiz API or a local Kokoro backend. Required tools (curl, python3) and optional tooling (yt-dlp, ffmpeg) match the documented features. Minor metadata mismatch: the registry lists no required env vars, but SKILL.md and the script require a NOIZ_API_KEY when using the Noiz backend.
✓
Instruction Scope
SKILL.md and the script limit actions to generating TTS, optionally uploading user-provided or downloaded reference audio to Noiz, and using local Kokoro when requested. The SKILL.md explicitly warns about copyright/privacy when sourcing reference audio. There are no instructions to read arbitrary system files or to exfiltrate unrelated data.
✓
Install Mechanism
No install spec is provided (instruction-only with an included script). The script itself uses standard system tools only; nothing is downloaded or executed from unknown URLs by the skill itself.
ℹ
Credentials
The only credential used is NOIZ_API_KEY (optional if you use the Noiz backend), which is proportional to the skill's external API use. The script will normalize and save the API key to ~/.noiz_api_key (mode 600) for convenience — this persistent storage is reasonable but should be understood by the user. Registry metadata not listing this env var is an inconsistency to be aware of.
✓
Persistence & Privilege
The skill does not request elevated privileges nor set always:true. Its only persistent action is writing the API key file in the user's home directory; it does not modify other skills or system-wide agent settings.
Assessment
This skill appears to do what it says: expressive TTS with optional voice cloning. Before installing, decide whether you want any audio/text to leave your machine. If you use the Noiz backend, the script will send text and any reference audio to https://noiz.ai/v1 and will save a normalized API key to ~/.noiz_api_key (file mode 600). If you must keep everything local, use the Kokoro backend. Be careful about sourcing reference audio from copyrighted or private material — the skill documents this risk. Finally, note the registry metadata didn't list NOIZ_API_KEY as a requirement while the SKILL.md and script use it; confirm you are comfortable providing that key before enabling the Noiz backend.

Like a lobster shell, security has layers — review code before you run it.

latestvk973grpg7t1qwmzz5nh0e2ya8h834566

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments