dd-tts-pack

dd-tts-pack is a skill for Claude Code from CaesiumY/dding-dong. It costs 86 tokens per session (8,499 once invoked), scanned B, original, MIT.

A wizard for creating text-to-speech sound packs with Qwen3-TTS, a system that turns written text into spoken audio. It supports cloning a reference voice or using a built-in voice.

In plain words
What is it for?
Creating WAV sound packs, choosing a cloned or built-in voice, checking the required environment, and configuring pack files and events.
Why use it?
It guides the setup needed to produce a collection of synthesized voice sounds instead of requiring each audio file to be made manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dding-dong plugin — 12 skills, 4 hooks shipped together

Good fit Creating WAV sound packs, choosing a cloned or built-in voice, checking the required environment, and configuring pack files and events.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add CaesiumY/dding-dong
Claude Code
/plugin install dding-dong

Made for: Claude Code.

Or install dding-dong, the plugin that ships this one along with the rest of its 12 skills, 4 hooks.

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 dd-tts-pack

README.md
[![agentmods](https://agentmods.dev/badge/skills/caesiumy/dding-dong/dd-tts-pack/github.svg)](https://agentmods.dev/skills/caesiumy/dding-dong/dd-tts-pack)
Your own site
<a href="https://agentmods.dev/skills/caesiumy/dding-dong/dd-tts-pack"><img src="https://agentmods.dev/badge/skills/caesiumy/dding-dong/dd-tts-pack/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 dd-tts-pack

Your own site · 80×15
<a href="https://agentmods.dev/skills/caesiumy/dding-dong/dd-tts-pack"><img src="https://agentmods.dev/badge/skills/caesiumy/dding-dong/dd-tts-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,499 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. 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 $0.00086 $0.08499
Opus 5 $0.00043 $0.04249
Sonnet 5 $0.00017 $0.01700
Haiku 4.5 $0.00009 $0.00850

Measured 9d ago against content hash 03cf2aec05e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

dd-tts-pack scanned grade B with 2 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 9d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/check-env.mjs, scripts/generate-tts.py, scripts/ref-text.mjs, …), 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt install -y {install_pkg}

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

> node -e "import('${CLAUDE_PLUGIN_ROOT}/scripts/core/platform.mjs').then(m => m.detect()).then(p => { const {execSync} = require('child_process'); execSync(p.audioPlayer + ' PACK_DIR/preview.wav'); })"
skills/dd-tts-pack/SKILL.md · 815 lines

How it starts

The opening of the file, as written. The whole thing — 815 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TTS 사운드 팩 생성 마법사

Qwen3-TTS를 사용하여 음성 합성 기반 사운드 팩을 생성합니다. 보이스 클로닝(참조 음성 복제) 또는 CustomVoice(내장 음성) 모드를 지원합니다.

설계 노트: disable-model-invocation은 의도적으로 생략되었습니다. 이 스킬은 사용자 입력 해석, 환경 검사 결과 분석, TTS 설정 구성에 모델 추론이 필수적입니다.

사운드 팩 구조 참고

매니페스트 스키마, 디렉토리 구조, WAV 사양 상세는 ../dd-pack-create/references/manifest-spec.md 참조.

핵심 규칙:

  • 이벤트 엔트리는 반드시 { "files": ["filename.wav"] } 형식
  • 미등록 이벤트는 events에서 키를 생략 (null 아님)
  • WAV 권장: 16-bit PCM, 44100Hz, mono, 1~3초

플래그 파싱

$ARGUMENTS에서 플래그를 확인합니다:

  • --help: 아래 사용법을 출력하고 종료합니다.

    TTS 사운드 팩 생성 마법사
    
    Qwen3-TTS로 음성 합성 기반 사운드 팩을 생성합니다.
    보이스 클로닝 또는 내장 음성(CustomVoice)을 선택할 수 있습니다.
    
    사용법: /dding-dong:dd-tts-pack [옵션]
    
    옵션:
      --clone          보이스 클로닝 모드로 바로 시작
      --custom         CustomVoice 모드로 바로 시작
      --help           이 도움말 표시
    
    필요 환경:
      - NVIDIA GPU (8GB+ VRAM)
      - Python 3.10+ (자동 venv 설치 지원)
      - qwen-tts (venv에 자동 설치)
    
    예시:
      /dding-dong:dd-tts-pack
      /dding-dong:dd-tts-pack --clone
      /dding-dong:dd-tts-pack --custom
    
  • --clone: 모드 선택을 건너뛰고 보이스 클로닝 모드로 진행합니다.

  • --custom: 모드 선택을 건너뛰고 CustomVoice 모드로 진행합니다.

실행 순서

1단계: 환경 검사

스킬이 호출되면 환경을 자동 검사합니다:

node "${CLAUDE_PLUGIN_ROOT}/skills/dd-tts-pack/scripts/check-env.mjs"

결과 JSON에서 all_ok, python_path, venv, gpu 필드를 확인합니다.

모두 통과 (all_ok: true): PYTHON_PATH 변수에 python_path 값을 저장하고 2단계로 진행합니다.

GPU 없음 (gpu.ok: false): GPU 없이는 TTS를 실행할 수 없으므로 즉시 종료합니다.

CUDA GPU가 필요합니다. 이 스킬은 NVIDIA GPU(CUDA)가 있는 환경에서만 사용 가능합니다.
기존 WAV 파일로 팩을 만들려면: /dding-dong:dd-pack-create

GPU 있고 venv 없음 (gpu.ok: true && venv.exists: false): 환경 상태를 표시한 후 자동 설치를 제안합니다.

TTS 사운드 팩 생성에는 다음 환경이 필요합니다:

  {venv.exists ? "✓" : "✗"} TTS 전용 환경     {venv.exists ? venv.path : "— 미설치 (자동 설치 가능)"}
  {python.ok ? "✓" : "✗"} Python 3.10+        {python.ok ? python.version + " (" + python.source + ")" : "— 미설치"}
  {qwen_tts.ok ? "✓" : "✗"} qwen-tts 패키지   {qwen_tts.ok ? qwen_tts.version : "— 미설치"}
  {GPU 상태에 따른 3가지 분기 — 아래 참조}

Read the full file on GitHub · 815 lines

Files

What ships with it

6 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. 9d ago First seen · 815 lines · 86 tokens per session scan B 03cf2aec05e0

Subscribe to this mod's changes

dd-tts-pack is a skill published in the GitHub repository CaesiumY/dding-dong (2 stars, last pushed 6mo ago), licensed MIT. It adds 86 tokens to every session and 8,499 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

gpt-image-cookbook

Use this skill whenever a user asks to generate, create, draw, render, or edit images with AI image models — gpt-image-2, DALL-E, Google Imagen, Flux, or others. Covers text-to-image, reference-image editing, inpainting, posters, typography, UI mockups, diagrams, and curated gallery prompts. Search the bundled…

eugeniughelbur/gpt-image-cookbook · 118 tokens

companion-pet

A skill for controlling a desktop companion called companion-pet for Claude Code or Codex. It can handle the pet's display, character images, spoken notifications, status, and installation.

OvOhao/companion-pet · 144 tokens

deepchat-cli

Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations. Activate when a user asks to invoke DeepChat capabilities that are not already exposed as a more specific tool, compare models, run a…

ThinkInAIXYZ/deepchat · 80 tokens

sheet-music-publisher

Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.

bitwize-music-studio/claude-ai-music-skills · 36 tokens

capcut-edit

Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draftcontent.json, draftinfo.json, or cutting videos.

renezander030/capcut-cli · 72 tokens

youtube-producer

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…

cbrock84/headcount · 86 tokens