wjs-voicedrop-reading-aloud SKILL.md skillA
wjs-voicedrop-reading-aloud from jianshuo/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jianshuo/claude-skills/wjs-voicedrop-reading-aloud@git:20260815.c35f717Pins git:20260815.c35f717 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jianshuo/claude-skills
- Path
wjs-voicedrop-reading-aloud/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260815.c35f717, committed Aug 15, 2026
- First version recorded
- Aug 14, 2026
- Size
- 6,579 bytes
- Repository stars
- 138
- License
- MIT
Use when the user wants text turned into an audiobook / read aloud — they give a passage, a file, a URL, or a VoiceDrop article and want an mp3 narration with expressive voices. Triggers — "做成有声书", "朗读出来", "读给我听", "念出来", "read aloud", "/wjs-voicedrop-reading-aloud".
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
# wjs-voicedrop-reading-aloud 文字 → 有声书 mp3。不是照字面念，而是先**编排**：不同性质的内容换不同声音，关键转折处加语音指令，然后用火山引擎豆包 seed-tts-2.0 合成。 合成工具：`~/code/volcano-tts/tts.py`（先 `source ~/code/.env`）。 ## 铁律 1. **绝不把带【】/[ ] 标注的文本直接喂裸 API** —— 裸 API 会把标注原样念出来（实测实锤）。永远走 `tts.py`，它把标注切段转成 `context_texts` 语音指令。 2. **只能用 2.0 音色（`_uranus_bigtts` 后缀）** —— moon/mars/tob 音色在 seed-tts-2.0 资源下报错 `resource ID is mismatched`。 3. **合成前把编排好的朗读脚本给用户看一眼**（除非用户说直接出）——编排是再创作，声音分配和指令值得确认。headless/自动化场景跳过此步。 ## 工作流 ### 1. 取内容并认真通读 - 纯文本/文件：直接读。 - URL：WebFetch；SPA 页面（如 docs.volcengine.com）用 browse skill 渲染后取正文。 - VoiceDrop 文章：voicedrop MCP 的 `read_article`。 通读时标记出：正文叙述 / 直接引用（引号、blockquote）/ 大白话吐槽与内心 OS / 数据、列表、表格 / 标题与小节。 ### 2. 编排重写成朗读脚本 这是核心步骤，是**重写**不是转录： - 去掉一切视觉残留：markdown 符号、链接、图片说明、脚注编号。 - 表格、列表、数据改写成口语句子（「三个原因：第一…」）。 - 标题不逐字念，化进过渡句，或用停顿+换气带过。 - 太书面的长句改口语，但保留作者的用词风格。 - **按内容性质分配音色**（见音色表）：正文一个主声贯穿；引用换引用声；吐槽/大白话换插话声。声音切换是给听众的「格式信号」，等价于视觉上的引用块。 - 不要频繁换声：一般 2~3 个声音封顶，切换只发生在内容性质真正变化处。 ### 3. 加语音指令（克制） 在句前加 `[心理活动、细腻表情、肢体动作等描述]`，如 `[放慢，一字一顿，点出要害]`。 - **只在需要的地方加**：情绪转折、节奏变化、重音、引用的口吻模仿。平铺直叙的段落一个不加，靠全局指令兜底。 - 经验密度：每 3~5 句最多一处；一段平静的叙述可以整段没有。 - 每处标注就是一次切段（一次 API 调用+拼接点），切太碎会让语流变散。 - 标注写成对朗读者说的表演提示（心理活动/表情/动作皆可），不要写成对听众的说明。 …
Read the whole file at its exact version.
How to install
mdr add jianshuo/claude-skills/wjs-voicedrop-reading-aloud@sha256:8bc12b129b0a9172The line at the top of this page pins the label git:20260815.c35f717, 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_yute7ljubjypp6dh)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 14, 2026 and Aug 15, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260815.c35f717 latest | 2026-08-15 | c35f717 | 6,579 B | A | view · diff |
| git:20260814.2bcb201 | 2026-08-14 | 2bcb201 | 6,431 B | A | view · diff |
| git:20260814.b6e3535 | 2026-08-14 | b6e3535 | 6,170 B | A | view · diff |
| git:20260814.391ebd9 | 2026-08-14 | 391ebd9 | 5,707 B | A | view · diff |
| git:20260814.703ad7a | 2026-08-14 | 703ad7a | 5,290 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 (6579 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
jianshuo/claude-skills · 138 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yute7ljubjypp6dh GET https://markdownregistry.com/api/v1/resolve?ref=jianshuo/claude-skills/wjs-voicedrop-reading-aloud GET https://markdownregistry.com/api/v1/blob/8bc12b129b0a91726ccc34e8574daa9d4c5d2c7f6b5a3963323842f18c829f45
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.