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.
npx skills add Elumenotion/GuideAnts --skill audiocpp-tts-controlsgit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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.
[](https://agentmods.dev/skills/elumenotion/guideants/audiocpp-tts-controls)<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-tts-controls"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-tts-controls/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.
<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-tts-controls"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-tts-controls.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.00682 |
| Opus 5 | $0.00042 | $0.00341 |
| Sonnet 5 | $0.00017 | $0.00136 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
audiocpp-tts-controls scanned grade A 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 6d ago.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8084/admin/voice-pack # wrapper's preset voice packs How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio.cpp synthesis controls (experimental)
The GuideAnts TTS wrapper contract is {text, voice, speed}. The raw engine
underneath (127.0.0.1:18084) accepts more. This skill calls it directly;
deliverables are WAV files in Output/, the live voice path is untouched.
Preflight
python3 Skills/audiocpp-tts-controls/scripts/preflight.py --for tts-controls
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.
The controls
All via one script (engine model id auto-detected from the wrapper's health):
python3 Skills/audiocpp-tts-controls/scripts/engine_tool.py speech "Hello there" \
-o out.wav \
[--seed 42] # deterministic, reproducible synthesis
[--language de] # force spoken language (family-specific values)
[--instructions "a calm, deep narrator voice"] # voice design — vdes-task models only
[--voice Vivian] # builtin speaker id
Notes:
--instructionsonly works on a model loaded with thevdestask (the VoiceDesign catalog entry). Other families reject it — the engine errors loudly; surface that text.--languagevalues are family-specific (name or code); the error text names what the family accepts.- Same text + same seed + same model ⇒ same audio. Useful for A/B-ing one parameter at a time.
Listing available voices
python3 Skills/audiocpp-tts-controls/scripts/engine_tool.py voices # engine's cached/builtin ids
curl -s http://127.0.0.1:8084/admin/voice-pack # wrapper's preset voice packs
curl -s http://127.0.0.1:8084/admin/voices # wrapper's builtin speaker list
Known gap: some families (e.g. Qwen3 CustomVoice) keep builtin speakers in the
model's own config, invisible to /v1/audio/voices — if the list comes back
empty, the model dir's config.json/generation_config.json has the truth.
Related
Voice cloning from a reference clip is the audiocpp-voice-clone skill; running model families GuideAnts doesn't ship is audiocpp-deferred-tts.
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.
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.
- 6d ago Changed a3d4a33a2cb6
- 10d ago First seen · 69 lines · 83 tokens per session scan A 43b3ccfd9c2f
audiocpp-tts-controls is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 682 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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".
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.
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.
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.
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.
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.