Skills ai-voice-cloning

📦

ai-voice-cloning

Name: ai-voice-cloning
Author: inference-sh-9

Content revision r1 Critical ⚙️ External commands🌐 Network access

Generate AI Voice Narration with inference.sh

Creating natural narration can require recording time and editing tools. This skill guides Claude, Codex, and Claude Code through inference.sh voice generation workflows.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "ai-voice-cloning" from https://skillstore.io/skills/inference-sh-9-ai-voice-cloning.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-ai-voice-cloning/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inference-sh-9-ai-voice-cloning.md Signed manifest GET /api/skills/inference-sh-9-ai-voice-cloning/manifest Signed lockfile GET /api/skills/inference-sh-9-ai-voice-cloning/lockfile

Test it

Using "ai-voice-cloning". A product demo script that needs a calm narrator.

Expected outcome:

Recommended model: Kokoro TTS.
Voice: af_nicole for clear professional delivery.
Pacing: normal speed with short sentences and clear pauses.

Using "ai-voice-cloning". A ten-minute lesson script for an online course.

Expected outcome:

The skill would propose chunk boundaries, a consistent voice, and merge guidance for a single narration track.

Using "ai-voice-cloning". A dialogue between host and guest for a podcast intro.

Expected outcome:

Speaker one uses a warm conversational voice.
Speaker two uses a brighter response voice.
Each speaker is generated separately before merging.

Security Audit

Critical

v5 • 7/9/2026 Open versioned report

Most external-command detections are Markdown backtick false positives, but the quick start confirms a critical curl-to-shell installer risk on line 16. The skill also uses remote inference services and lacks explicit consent guardrails for synthetic voice or avatar workflows.

Files scanned

274

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

Critical

SKILL.md:16

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh && infsh login

The quick start pipes a remote installer directly into sh. This is a classic arbitrary code execution and supply-chain compromise pattern.

Medium

SKILL.md:3-4 SKILL.md:180-193

Synthetic Voice Impersonation Guardrails Missing

The skill markets voice cloning and documents talking-head generation, but it does not require consent or prohibit impersonation. This creates an abuse path for unauthorized voice or avatar content.

The cited lines directly describe voice cloning triggers and a portrait-to-talking-head workflow. The examples are benign, so the finding focuses on missing guardrails rather than proven malicious intent.

Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Critical

SKILL.md:16

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh && infsh login

The URL is used in a curl pipeline into sh, so a remote script from cli.inference.sh executes on the user machine. A compromised endpoint could run arbitrary code.

Low

SKILL.md:11

Hardcoded URL

![AI Voice Generation](https://cloud.inference.sh/u/4mg21r6ta37mpaz6ktzwtt8krr/01jz00krptarq4bwm89g5

The Markdown image references cloud.inference.sh and may fetch third-party content when rendered. This creates a low-severity privacy and remote-content dependency risk.

Risk Factors

⚙️ External commands (48)

🌐 Network access (6)

SKILL.md:9 SKILL.md:11 SKILL.md:16 SKILL.md:25 SKILL.md:175 SKILL.md:191

Detected Patterns

Pipe to shell pattern

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/inference-sh-9-ai-voice-cloning/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-9-ai-voice-cloning/security.svg)](https://skillstore.io/skills/inference-sh-9-ai-voice-cloning?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-9-ai-voice-cloning?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-ai-voice-cloning/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-9-ai-voice-cloning.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

inference-sh-9. (2026). ai-voice-cloning security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-ai-voice-cloning/audits/5

BibTeX citation

@techreport{inference-sh-9-inference-sh-9-ai-voice-cloning-2026,
  author = {inference-sh-9},
  title = {ai-voice-cloning security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/inference-sh-9-ai-voice-cloning/audits/5},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-voice-cloning security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "inference-sh-9"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/inference-sh-9-ai-voice-cloning/audits/5"
identifiers:
  - type: other
    value: "skillstore:inference-sh-9-ai-voice-cloning:audit:5"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

inference-sh Recommended

inference-sh-ai-voice-cloning

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 41

Updated

2026-09-09

inference-sh-9 Current

inference-sh-9-ai-voice-cloning

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-09-09

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Produce Video Narration

Generate short voiceovers and merge them with existing video assets.

Create Course Audio

Turn lesson scripts into paced narration with selected voices.

Prototype Podcast Dialogue

Create separate speaker tracks and merge them for draft podcast segments.

Try These Prompts

Generate a Short Voiceover

Use this skill to generate a 30-second voiceover from this script: [paste script]. Choose a clear professional voice and explain the selected model.

Compare Voice Options

Create three TTS variants for this paragraph using different Kokoro voices. Describe tone, pacing, and best fit for each.

Build a Long Narration Plan

Split this long script into safe chunks, recommend one consistent voice, and prepare generation steps for each chunk.

Create a Multi-Speaker Workflow

Design a two-speaker audio workflow for this dialogue, including voice choices, pacing notes, and merge steps.

Best Practices

Obtain written consent for any real person voice, likeness, portrait, or protected script.
Start with a short sample before generating long narration.
Use punctuation and speed settings to control pacing.

Avoid

Do not imitate a real person without permission.
Do not run remote installer commands without verifying the source and checksum.
Do not paste private scripts or regulated data into remote generation prompts.

Frequently Asked Questions

Does this skill clone a specific person?

The documented examples use preset TTS voices. Any real-person cloning or avatar use requires explicit rights and consent.

Does it require inference.sh?

Yes. The workflows depend on the inference.sh CLI and remote app services.

Can Claude, Codex, or Claude Code use it?

Yes. The skill metadata lists Claude, Codex, and Claude Code as supported tools.

Can it make long audiobooks?

It can plan chunked generation and audio merging. Very long projects still need review for consistency and rights.

Is the installer safe to run automatically?

No. The quick start uses a curl pipe-to-shell command. Use verified manual installation instead.

Does it create video avatars?

It includes a talking-head workflow using a portrait image and generated speech. Use it only with permitted images.

Developer Details

Author

inference-sh-9

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh-9/skills/tree/main/skills/ai-voice-cloning/

Ref

3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88

Maintenance freshness

7/18/2026

Usage

8 downloads · 132 views

File structure

📄 SKILL.md