Kids AI Magazine (学前亲子AI电子杂志)
Generate interactive HTML magazines that turn AI news into stories for 3-6 year olds, with TTS audio narration.
Workflow
1. Collect News
Gather 3-5 current AI news items from reliable sources (36氪, 澎湃, TechCrunch, etc.). For each item, extract:
- - Core fact (one sentence)
- Why it matters
- Source URL
2. Adapt Stories
Transform each news item into a kids story. Each story needs:
- - Title: Fun, curiosity-driven (e.g., "机器人宝宝学走路啦!")
- Paragraphs: 2-3 short paragraphs, use analogies to things kids know (bikes, scissors, building blocks)
- TTS text: Pure Chinese narration text, no English words (replace "AI" → "智能技术", "GPU" → "芯片"), add verbal cues ("你知道吗?", "是不是很神奇呀?")
- Parent-child dialogue: 2 Q&A pairs (child asks naive question → parent gives educational answer)
- Parent note: Brief context for parents + source link
- Icon: One emoji per story
3. Generate Audio
Prerequisite: INLINECODE0
CODEBLOCK0
Voices: zh-CN-XiaoxiaoNeural (女声, recommended), zh-CN-YunxiNeural (男声), zh-CN-XiaoyiNeural (女童声)
TTS text rules:
- - No English words (TTS reads them letter by letter)
- Add pauses with commas and periods
- Use onomatopoeia: "噗通!摔倒啦!"
- Warm narrator tone: "小朋友们好呀~"
4. Build HTML
Use assets/template.html as the base. The template includes:
- - Colorful header with rainbow gradient
- Story cards with embedded audio players
- Parent-child dialogue bubbles
- Activity section, nursery rhyme, quiz
- Mobile-responsive design
For custom builds: INLINECODE5
5. Serve & Share
CODEBLOCK1
Story JSON Format
See references/example-stories.json for a complete 3-story example. Key fields:
CODEBLOCK2
Design Principles
- 1. No scary content — only positive, wonder-inspiring stories
- Analogy-first — explain everything through things kids already know
- Emotion boundary — always clarify: computers are smart but have no feelings
- Parent empowerment — every story gives parents a conversation hook
- Audio-first — assume kids can't read; audio must stand alone
Kids AI Magazine (学前亲子AI电子杂志)
生成互动式HTML杂志,将AI新闻转化为3-6岁儿童的故事,配有TTS语音朗读。
工作流程
1. 收集新闻
从可靠来源(36氪、澎湃、TechCrunch等)收集3-5条当前AI新闻。对每条新闻提取:
2. 改编故事
将每条新闻转化为儿童故事。每个故事需要:
- - 标题:有趣、充满好奇心(例如:机器人宝宝学走路啦!)
- 段落:2-3个短段落,使用孩子熟悉的事物做类比(自行车、剪刀、积木)
- TTS文本:纯中文朗读文本,无英文单词(将AI替换为智能技术,GPU替换为芯片),加入口语提示词(你知道吗?、是不是很神奇呀?)
- 亲子对话:2组问答(孩子问天真的问题 → 家长给出教育性回答)
- 家长笔记:给家长的简要背景说明 + 来源链接
- 图标:每个故事一个表情符号
3. 生成音频
前提条件:pip3 install edge-tts
bash
python3 scripts/generate_audio.py --stories stories.json --voice zh-CN-XiaoxiaoNeural --output-dir ./output
语音选项:zh-CN-XiaoxiaoNeural(女声,推荐)、zh-CN-YunxiNeural(男声)、zh-CN-XiaoyiNeural(女童声)
TTS文本规则:
- - 无英文单词(TTS会逐字母朗读)
- 用逗号和句号添加停顿
- 使用拟声词:噗通!摔倒啦!
- 温暖的讲述者语气:小朋友们好呀~
4. 构建HTML
使用assets/template.html作为基础模板。模板包含:
- - 彩虹渐变的彩色标题
- 带有嵌入式音频播放器的故事卡片
- 亲子对话气泡
- 活动板块、儿歌、问答
- 移动端响应式设计
自定义构建:python3 scripts/build_magazine.py --stories stories.json --template assets/template.html --output output/index.html
5. 服务与分享
bash
本地预览
python3 -m http.server 8899 -d ./output
公开分享(安装一次:brew install cloudflared)
cloudflared tunnel --url http://localhost:8899
故事JSON格式
参见references/example-stories.json获取完整的3个故事示例。关键字段:
json
{
title: 故事标题,
icon: 🤖,
paragraphs: [HTML段落1, 段落2],
tts_text: 纯中文朗读文本,无英文,
dialogue: [
{role: child, avatar: 👶, text: 问题},
{role: parent, avatar: 👩, text: 回答}
],
parent_note: 给家长的背景说明,
source_name: 来源名,
source_url: https://...
}
设计原则
- 1. 无恐怖内容 — 只有积极、激发好奇心的故事
- 类比优先 — 通过孩子已知的事物解释一切
- 情感边界 — 始终明确:计算机很聪明但没有感情
- 赋能家长 — 每个故事都给家长提供对话切入点
- 音频优先 — 假设孩子不识字;音频必须能独立存在