tts-voice-design SKILL.md skillA
tts-voice-design from swotatmk/infinite-creation is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add swotatmk/infinite-creation/tts-voice-design@git:20261008.d040fb3Pins git:20261008.d040fb3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- swotatmk/infinite-creation
- Path
skills/tts-voice-design/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261008.d040fb3, committed Oct 8, 2026
- First version recorded
- Sep 28, 2026
- Size
- 2,539 bytes
- Repository stars
- 105
- License
- MIT
为 Qwen3-TTS 音色设计工作流编写人物音色参数。使用时机：为漫剧人物设计专属音色（音色样本 voice_ref），需给出代表性台词 text 与音色描述 voice_description。输出 text 与 voice_description。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 人物音色设计（Qwen3-TTS）
为每个出场人物设计一个专属音色样本，供后续视频生成时作为 `voice_ref` 参考。
## 输入
- 人物 bible.md 中的 voice 特征（若有）。
- 人物在本章的对白风格（年龄、性别、性格、情绪基调）。
## 先决条件：asset 的 voice_desc（声音画像）
设计音色前，角色资产应带有 `voice_desc`（声音特征描述，性别+年龄段+音色质感，如 `青年男性，嗓音低沉`）：
- 若创建角色资产时未传 `voice_desc`，先调用 `update_asset(asset_id, { voice_desc })` 补充——这样 `design_voice` 才能拿到角色性别/年龄，生成后音色才与角色一致（男主不会变成女声）。
- `voice_desc` 与 `description` 不同：description 是外貌（给文生图），voice_desc 是声音（给 TTS）。不要混用。
## text（朗读文案 · 简短自我介绍）
写 1 句 **20~30 字左右的简短自我介绍**（约 5 秒，口语化、贴合人物语气），作为人物朗读的音色合成样本。示例：`你好呀，我是沈舒妍，喜欢安静的午后和温暖的光，很高兴认识你。`
**禁止长篇大论**：不要塞大段台词、剧情或描写，20~30 字即可；文案过长会生成过长的音色样本。
## voice_description（音色描述 · 不限制字数）
描述目标音色，**不限制字数**，可详细写，覆盖：性别 + 年龄段 + 音色质感（明亮/低沉/沙哑/清亮/温润）+ 语速 + 语气情绪 + 口音/风格。示例：`青年男性，嗓音低沉温和，语速偏慢，带一点书卷气的平静口吻`。
## 输出与调用
对每个人物输出 `{"text":"...","voice_description":"..."}`，然后调用 `design_voice(asset_id, text, voice_description)` 生成音色样本（落盘为该项目 voice_ref）。多个角色连续调用 design_voice，避免中途切回生图工作流造成模型重载。
## 约束
- 音色与人物年龄/性别/性格一致；不同角色音色尽量区分。
- voice_description 中文、具体，避免「好听」这类空词。
- **voice_description 必须包含性别与年龄段**（如「青年男性」「老年女性」），缺失时 TTS 会自由发挥成年轻女声。Read the whole file at its exact version.
How to install
mdr add swotatmk/infinite-creation/tts-voice-design@sha256:6008a03fd400c6f4The line at the top of this page pins the label git:20261008.d040fb3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_sbfrcc5ygpmulb4i)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 28, 2026 and Oct 8, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261008.d040fb3 latest | 2026-10-08 | d040fb3 | 2,539 B | A | view · diff |
| git:20260928.9936779 | 2026-09-28 | 9936779 | 1,812 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2539 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
swotatmk/infinite-creation · 105 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sbfrcc5ygpmulb4i GET https://markdownregistry.com/api/v1/resolve?ref=swotatmk/infinite-creation/tts-voice-design GET https://markdownregistry.com/api/v1/blob/6008a03fd400c6f4c2abb177f259e1d8dee1ab29529ddd2af4b07559deaad048
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.