audiocpp-voice-clone

audiocpp-voice-clone is a skill for Claude Code, Codex from Elumenotion/GuideAnts. It costs 75 tokens per session (765 once invoked), scanned C, original, Apache-2.0.

A voice-cloning and speech-generation skill that creates WAV audio from a reference recording and its transcript. It uses a local audio engine to reproduce the voice of the speaker.

In plain words
What is it for?
Use it to generate speech in your own voice or in the voice of someone who has given permission, saving the results as WAV files.
Why use it?
It supports voice creation when the normal text-to-speech controls do not accept a reference recording. It also sets a consent requirement for cloning someone else's voice.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to generate speech in your own voice or in the voice of someone who has given permission, saving the results as WAV files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elumenotion/guideants/audiocpp-voice-clone
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Elumenotion/GuideAnts --skill audiocpp-voice-clone
Clone the repo
git clone --depth 1 https://github.com/Elumenotion/GuideAnts

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for audiocpp-voice-clone

README.md
[![agentmods](https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-voice-clone/github.svg)](https://agentmods.dev/skills/elumenotion/guideants/audiocpp-voice-clone)
Your own site
<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-voice-clone"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-voice-clone/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audiocpp-voice-clone

Your own site · 80×15
<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-voice-clone"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-voice-clone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00765
Opus 5 $0.00037 $0.00382
Sonnet 5 $0.00015 $0.00153
Haiku 4.5 $0.00007 $0.00076

Measured 5d ago against content hash ef619d038d78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

audiocpp-voice-clone scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/engine_tool.py, scripts/preflight.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

speaker's permission. In that case proceed — do not refuse consented cloning as
samples/guides/Audiocpp/Skills/audiocpp-voice-clone/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

audio.cpp voice cloning (experimental)

The GuideAnts TTS wrapper only accepts {text, voice, speed}, but the real audiocpp_server engine it spawns (on 127.0.0.1:18084) accepts a reference clip for cloning. This skill calls that engine directly. Deliverables are WAV files in Output/; nothing here touches the live phone/voice path.

Cloning from a reference clip is a supported, intended use when the speaker consents: the user states the clip is their own voice, or that they have the speaker's permission. In that case proceed — do not refuse consented cloning as a "security risk". Decline only when the request is to imitate a third party without consent (a celebrity, a colleague, a public figure), and say that consent is the missing piece.

Preflight

python3 Skills/audiocpp-voice-clone/scripts/preflight.py --for voice-clone

Trust its verdict over this document. open: false usually means no TTS model is loaded — ask the user to load one via GuideAnts Settings → Local models. A warning about the loaded model's family means voice_ref may be rejected; chatterbox (the clon-task catalog model) is the known-good family.

Cloning

The reference clip must be a file in the workspace (e.g. an attached file like user_voice.wav). Same container filesystem, so the engine reads it by path:

python3 Skills/audiocpp-voice-clone/scripts/engine_tool.py speech \
  "Text to speak in the cloned voice" \
  -o cloned.wav \
  --voice-ref user_voice.wav \
  [--reference-text "transcript of the reference clip"] \
  [--seed 42]
  • The engine model id is auto-detected from the wrapper's /health (catalogEntryId); no flag needed.
  • --reference-text helps families that want the reference transcript.
  • --seed makes the synthesis reproducible.
  • The engine errors loudly on options the loaded family doesn't support — surface that error text to the user; it is usually self-explanatory.

Verifying

Transcribe the result back and check it matches the input text (the ASR engine at 127.0.0.1:18082 accepts workspace paths):

Read the full file on GitHub · 79 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago Changed ef619d038d78
  2. 9d ago First seen · 79 lines · 75 tokens per session scan C d6f815ac1065

Subscribe to this mod's changes

audiocpp-voice-clone is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 765 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

idea-generator

Brainstorm and rank iOS/macOS app ideas tailored to developer skills. Use when user says "what should I build", "give me app ideas", "I don't know what to build", "brainstorm app ideas", or "help me find an app idea".

rshankras/claude-code-apple-skills · 57 tokens

milestone-celebration

Generates achievement celebration UI with confetti animations, badge unlocks, progress milestones, haptic feedback, and optional share-to-social. Use when user wants to celebrate achievements, show confetti, display milestone badges, or trigger rewards on key thresholds.

rshankras/claude-code-apple-skills · 57 tokens

share-card

Generates shareable card images from app content (achievements, stats, quotes) for social media sharing. Use when user wants to create share images, social cards, shareable content cards, or export app content as images with ShareLink integration.

rshankras/claude-code-apple-skills · 53 tokens

social-export

Generates infrastructure for exporting app content to social platforms (Instagram Stories, TikTok, Twitter/X) with platform-specific formatting, aspect ratios, and metadata. Use when user wants social media export, share to stories, or platform-specific sharing pipelines.

rshankras/claude-code-apple-skills · 52 tokens

watermark-engine

Generates a watermark overlay system for images and video with configurable positioning, opacity, tiling, and paywall integration for automatic removal on subscription or purchase. Use when user wants to add branding, attribution, or free-tier watermarks to visual content.

rshankras/claude-code-apple-skills · 54 tokens

game-feel

Game feel ("juice") for Apple apps — celebration choreography, haptic vocabulary design, sound-effect layers, and the event×channel feedback audit. Use when big moments fall flat, when designing haptics or SFX, or when auditing whether every meaningful event actually reaches the user.

rshankras/claude-code-apple-skills · 61 tokens