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-host-ttsgit 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-host-tts)<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-host-tts"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-host-tts/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-host-tts"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-host-tts.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 | $0.00075 | $0.00657 |
| Opus 5 | $0.00037 | $0.00329 |
| Sonnet 5 | $0.00015 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
audiocpp-host-tts scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio.cpp host-native engine (experimental)
The sandbox can reach an audiocpp_server the user runs natively on the host —
same raw API as the container engines, but with whatever models and loaders
their build has (e.g. a fork compiled with Kokoro enabled). Deliverables are
WAV files in Output/.
Preflight
python3 Skills/audiocpp-host-tts/scripts/preflight.py --for host-tts
Resolution order: AUDIOCPP_ENGINE_URL env (set via the guide editor's
Environment variables UI), else http://host.docker.internal:8080. The
preflight also distinguishes a real audio engine from a llama-server that
happens to answer /health on the same port.
Synthesizing
--model is required — there is no wrapper to auto-detect from:
python3 Skills/audiocpp-host-tts/scripts/engine_tool.py speech "Hello" \
--engine-url http://host.docker.internal:8080 --model <engine-model-id> \
-o hello.wav [--voice <id>] [--seed 42] [--language en] [--voice-ref ...]
List the models the host build serves: GET <base>/v1/models; voices:
engine_tool.py voices --engine-url <base> --model <id>.
The consent rule applies to --voice-ref cloning here too: proceed for the
user's own voice or a consenting speaker; decline third-party imitation.
Hard limit: TTS only
The host engine's /v1/audio/transcriptions takes a server-local path in its
JSON body — files in this sandbox are not visible to the host process, so
transcription against the host engine cannot work from here. Use the container
ASR (the audiocpp-asr-extended skill) instead.
Troubleshooting
| Symptom | Likely cause | What to do |
|---|---|---|
| Unreachable | Server not bound to 0.0.0.0, or Windows Firewall blocking the Docker adapter |
Ask the user to check both |
/health 200 but no /v1/audio/* |
A llama-server on that port, not audiocpp | Ask which port their audio.cpp build listens on |
| Model errors | Family/option mismatch in their build | Surface the engine's error text — it names the problem |
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 25c10332f155
- 10d ago First seen · 64 lines · 75 tokens per session scan A 63908815b9d8
audiocpp-host-tts 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 657 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. 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.