audiocpp-asr-extended

audiocpp-asr-extended is a skill for Claude Code, Codex from Elumenotion/GuideAnts. It costs 88 tokens per session (820 once invoked), scanned A, original, Apache-2.0.

An experimental audio transcription tool that converts workspace audio files into text. It can read files by path, accept language hints, and use additional Qwen3-family speech-recognition model snapshots.

In plain words
What is it for?
Use it to transcribe large or locally stored WAV files, provide hints such as German, or test another supported Qwen3-family speech-recognition model.
Why use it?
It supports files that cannot be sent through the normal upload route and allows the transcription language to be specified. It also provides a way to use model snapshots not listed by the standard catalogue.

Skill for Claude CodeCodex

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

Good fit Use it to transcribe large or locally stored WAV files, provide hints such as German, or test another supported Qwen3-family speech-recognition model.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr-extended/github.svg)](https://agentmods.dev/skills/elumenotion/guideants/audiocpp-asr-extended)
Your own site
<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-asr-extended"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr-extended/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-asr-extended

Your own site · 80×15
<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-asr-extended"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr-extended.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 820 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 54
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00088 $0.00820
Opus 5 $0.00044 $0.00410
Sonnet 5 $0.00018 $0.00164
Haiku 4.5 $0.00009 $0.00082

Measured 7d ago against content hash 9e437eb44e06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audiocpp-asr-extended 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 7d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/engine_tool.py, scripts/fetch_model.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://127.0.0.1:8082/admin/load \
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

samples/guides/Audiocpp/Skills/audiocpp-asr-extended/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 extended ASR (experimental)

The GuideAnts ASR wrapper (127.0.0.1:8082) takes multipart uploads with no language control. The raw engine it spawns (127.0.0.1:18082) accepts a server-local path and a language hint — and the sandbox shares its filesystem, so any workspace file qualifies. The wrapper also loads bare model directories the catalog doesn't list (unlike the strictly-gated TTS wrapper).

Preflight

python3 Skills/audiocpp-asr-extended/scripts/preflight.py --for asr-extended

Trust its verdict over this document. open: false means no ASR model is loaded — ask the user to load one via GuideAnts Settings → Local models. Warnings tell you whether the sideload path (below) is available.

Transcribing by path (with language hint)

python3 Skills/audiocpp-asr-extended/scripts/engine_tool.py transcribe \
  clip.wav [--language de]
  • No upload and no gateway size cap — the engine reads the file in place.
  • The engine model id is always qwen3-asr (fixed by the wrapper), whatever snapshot is actually loaded.
  • Input should be WAV for the raw engine; for other formats, either convert with ffmpeg first or use the wrapper upload (POST :8082/transcribe, multipart field audio), which re-encodes to 16 kHz mono itself.

Sideloading a non-catalog ASR snapshot

The ASR wrapper's /admin/load accepts any bare directory under /models-local/asr whose leaf name matches the model_id. The engine family defaults to qwen3_asr, so only qwen3_asr-family snapshots work (other families would need the GA_ASR_ENGINE_FAMILY env at service start — a compose change, out of skill scope).

python3 Skills/audiocpp-asr-extended/scripts/fetch_model.py <hf-repo-id> \
  --dest /models-local/asr/<DirName>
curl -s -X POST http://127.0.0.1:8082/admin/load \
  -H "Content-Type: application/json" -d '{"model_id": "<DirName>"}'

Warning — this replaces the user's loaded ASR model. Ask before doing it, and offer to restore afterwards:

Read the full file on GitHub · 79 lines

Files

What ships with it

3 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. 7d ago Changed 9e437eb44e06
  2. 11d ago First seen · 79 lines · 88 tokens per session scan A 948263528783

Subscribe to this mod's changes

audiocpp-asr-extended is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 820 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.

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