wjs-converting-text-to-video
This skill converts a written article into a polished short-form video optimized for vertical platforms. It combines Volcano TTS Chinese narration, HyperFrames-powered scene animations, and AI-generated abstract watercolor backgrounds to produce 1080×1920 MP4 files ready for YouTube Shorts, TikTok, and similar services. The output emphasizes visual contrast and pacing over template repetition, enforcing diverse layouts and typography across 5–10 scenes.
wjs-converting-text-to-video transforms Chinese articles into 1080×1920 portrait MP4 videos with TTS narration, animated text, and watercolor backgrounds.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-23
wjs-converting-text-to-video transforms Chinese articles into 1080×1920 portrait MP4 videos with TTS narration, animated text, and watercolor backgrounds. This skill converts a written article into a polished short-form video optimized for vertical platforms. It combines Volcano TTS Chinese narration, HyperFrames-powered scene animations, and AI-generated abstract watercolor backgrounds to produce 1080×1920 MP4 files ready for YouTube Shorts, TikTok, and similar services. The output emphasizes visual contrast and pacing over template repetition, enforcing diverse layouts and typography across 5–10 scenes.
Use it when
- Yes.
- wjs-converting-text-to-video generates vertical portrait video in 1080×1920 resolution as MP4 files, sized for YouTube Shorts, TikTok.
Verify before relying
Read SKILL.md below before installing (9 files). Open directory: indexed for reading, not audited.
Similar skills
Install
jianshuo/claude-skills/wjs-converting-text-to-video · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does wjs-converting-text-to-video do?
wjs-converting-text-to-video transforms written articles into polished short-form MP4 videos optimized for vertical platforms like YouTube Shorts and TikTok. It combines Volcano TTS Chinese narration, HyperFrames-powered scene animations, and AI-generated abstract watercolor backgrounds to produce 1080×1920 videos that emphasize visual contrast and pacing across 5–10 scenes.
Can I turn text into short video with TTS narration using this skill?
Yes. wjs-converting-text-to-video accepts markdown or article text and automatically generates narrated video with text-to-speech. It supports Chinese voiceover via Volcano TTS, handles scene segmentation, and outputs MP4 files ready for social platforms—no manual narration recording required.
What output format and dimensions does wjs-converting-text-to-video produce?
wjs-converting-text-to-video generates vertical portrait video in 1080×1920 resolution as MP4 files, sized for YouTube Shorts, TikTok, and WeChat. Video length typically ranges from 30–90 seconds, with content divided across 5–10 dynamically laid-out scenes rather than repetitive templates.
Does wjs-converting-text-to-video support Chinese voiceover?
Yes. wjs-converting-text-to-video creates narrated video with Chinese voiceover powered by Volcano TTS. It automatically segments your article, generates speech, and syncs narration to animated scenes with watercolor backgrounds and motion graphics for a polished, platform-ready result.
How does wjs-converting-text-to-video handle visual design?
wjs-converting-text-to-video enforces diverse layouts and typography across scenes to avoid template repetition. It uses AI-generated abstract watercolor backgrounds, HyperFrames-powered animations, and visual contrast to create dynamic 30–90 second videos that stand out on social media feeds.
Can wjs-converting-text-to-video automate my article-to-social-media workflow?
Yes. wjs-converting-text-to-video automates the article-to-social-media video pipeline by accepting markdown or text input and producing finished MP4 files in a single pass. This eliminates manual scene creation, narration recording, and editing—ideal for scaling content across YouTube Shorts, TikTok, and WeChat.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
wjs-converting-text-to-video
把一篇王建硕风格的微信公众号 article.md 做成 1080×1920 竖屏、30-90 秒 的中文解说短视频：TTS 旁白 + HyperFrames CSS/GSAP 动画 + 抽象水彩背景 + 转场 SFX。输出 MP4 给视频号 / 抖音 / 小红书 / Reels。
What this skill produces
| 维度 | 默认 |
|---|---|
| 尺寸 | 1080×1920 竖屏 (9:16) |
| 时长 | 30-90 秒 |
| Scene 数 | 5-10 |
| 旁白 | 火山引擎 Volcano TTS，默认阿虎对话男声 |
| 背景 | GPT Image 2 生成的抽象水彩 (bg.png) + blur 30 + 暖黑半透明 overlay |
| 字体 | Noto Sans SC，hero 900，主文字暖奶白 |
| 输出 | <article-folder>/<slug>.mp4（与 video/ 平行，不放 video/ 里） |
| 发布 | 自动上传到 YouTube — Portrait → Shorts，Landscape → 普通 video；重新渲染会替换老视频（不累积） |
When this skill fires
- 用户已有
article.md，说「做成视频」「做一个解说」「讲一遍」 - 用户跑
/wjs-converting-text-to-video <article-folder> - 用户说「把昨天发的那 X 篇都做成视频」之类的批量请求
When NOT to use
- 没有文章稿，只是一个想法 → 先用
(truncated - see the full file via the links below)
File tree — 9 files
wjs-converting-text-to-video/SKILL.md
wjs-converting-text-to-video/scripts/bootstrap-project.sh
wjs-converting-text-to-video/scripts/daily-upload-batch.sh
wjs-converting-text-to-video/scripts/generate-bg.sh
wjs-converting-text-to-video/scripts/publish-to-youtube.py
wjs-converting-text-to-video/scripts/retrofit-bg-image.py
wjs-converting-text-to-video/scripts/strip-dark-scene-bgs.py
wjs-converting-text-to-video/scripts/synth-sfx.sh
wjs-converting-text-to-video/scripts/tts.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Convert written article into animated short video with TTS narration”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
General Video is the catch-all composition authoring workflow for HyperFrames when no specialized template fits your input. Route specific requests (product launches, explainers, GitHub PRs, motion graphics) to their dedicated skills first; use this for freeform, multi-scene, or custom-length pieces. It guides you through design system setup, prompt expansion, planning, and layout before animation.
HyperFrames lets you build video compositions, animations, and effects entirely in HTML with data attributes and GSAP timelines. Author captions synced to audio, generate voiceovers, create beat-reactive animations, and add transitions—all by treating HTML as your video source of truth.
HyperFrames treats HTML as the source for video production, letting you author compositions with GSAP timelines for animation, data attributes for timing, and CSS for styling. Build title cards, overlays, captions, text-to-speech narration, beat-synced visuals, and scene transitions—then render to video. The framework handles clip visibility, media playback, and timeline synchronization across your composition.
HyperFrames treats HTML as the source of truth for video production. Create compositions with data attributes for timing, GSAP animations, and CSS styling to produce title cards, overlays, captions, voiceovers, audio-reactive effects, and scene transitions. The framework manages clip visibility, media playback, and timeline synchronization across your entire video workflow.
This skill transforms individual subject concepts into two synchronized animated formats rendered by HyperFrames: a narrated teaching video (~90s, 1080p with Chinese voiceover and subtitles) and a silent looping animation (~32s, 1080p for embedding). Both outputs share a single HTML structure, unified storyboard, and thematic color palette across nine subject domains.
Compose post-production overlays—captions, covers, illustrations, and calls-to-action—directly onto video clips using HyperFrames, rendering everything in one pass to preserve quality. Works seamlessly downstream of segmentation workflows, turning raw clips into upload-ready MP4s with HTML/CSS captions, AI-generated covers, and timed motion graphics.
More skills wjs-reframing-video (MIT) · wjs-segmenting-video (MIT) · wjs-localizing-video (MIT) · wjs-burning-subtitles (MIT)