anything2explainer
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
原始仓库简介 · 中文摘要待补充 · agent-skills / ai-agents / ai-video / claude-code / claude-code-skill / codex
README / 项目原文
anything2explainer
English | 简体中文
Topic in, narrated explainer video out. anything2explainer is a Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar, in Chinese or English. Every frame is drawn in code with Remotion (React + TypeScript). No stock footage, no generative video model, no frames lifted from anyone else's work.
It is not a CLI. What ships here is the whole method an AI coding agent needs to finish the film: a compilable Remotion template, a primitives and lighting library, tooling for voiceover / storyboard / rendering / quantitative QC, written style and motion specs, a multi-agent division-of-labour protocol, and one complete reference film as the quality bar.
English cut — RAG & Knowledge Bases, 5′02″, 44 lines / 785 words, voiced by kokoro-82m am_liam at natural speed:
https://github.com/user-attachments/assets/e2771c68-a28c-4459-ac5a-a5b685181eeb
Chinese cut — RAG 与知识库 v2, 4′54″, 44 lines / 1490 characters, dot-field backdrop (bg: 'dots'), voiced through the bring-your-own-TTS path (Volcengine TTS 2.0 + forced alignment):
https://github.com/user-attachments/assets/5c213990-cbba-439e-8371-fbb3aa348e05
Both cuts share one storyboard and 44 shots; the English cut re-times every shot to the English voiceover. The full paper trail of the original Chinese cut (4′35″, star-field backdrop, 8 build agents in parallel for 40 minutes, two QC rounds) lives in examples/rag/ (research → narration → storyboard → shot source → QC reports → delivery notes); rendered frames are in examples/rag/frames/.
What it does
- Input: a topic ("explain vector databases"), or an article / document you want turned into a video. You also pick the length and the language.
- Output: a 1280×720 H.264 MP4 with synchronized voiceover, word-boundary-aligned subtitles, chapter cards, a top HUD and a bottom chapter progress bar, plus the full paper trail (research doc with sources, narration, storyboard, per-shot source code, QC reports).
- How: the agent researches the topic with sources, writes the narration, generates the voiceover and frame-accurate timeline, storyboards every shot, then dispatches parallel build agents that write one Remotion component per shot. QC agents review the rendered frames against written criteria before delivery.
- Time: roughly 1 to 3 hours of wall clock depending on length, most of it agents building shots in parallel. You are consulted at exactly four checkpoints.
Output spec
| Frame / rate | 1280×720 @ 30fps, H.264 |
| Length | your call (see table below); 2–8 minutes all work |
| Language | Chinese or English (lang in src/config.ts); typography, subtitle budgets and TTS switch with it |
| Look | black canvas with one of two backdrops, star field + fog gradient or dot-field wave (bg in src/config.ts; the dot-field wave is ported from video-talkcraft); white line art + purple accents; ultra-bold headline type |
| Persistent layers | 44px white-on-black-stroke subtitles, bottom chapter progress bar, top capsule HUD, optional pipeline rail, built by Anything2Explainer skill end credit (builtBy, set to '' to drop) |
| Voiceover | Chinese: edge-tts zh-CN-YunxiNeural (Yunxi, male, unmodified rate ≈5.5 chars/s). English: kokoro-82m am_liam (Liam, male). Or bring your own TTS / finished audio |
Length drives how much ground the film covers, and the size of the whole pipeline:
| Length | Chinese chars | English words | Lines / shots | Build agents | Wall clock | Disk |
|---|---|---|---|---|---|---|
| 2–3 min | 650–880 | 280–420 | 24–32 | 4–6 | ≈1 h | ≈2 GB |
| 3–5 min (reference tier) | 1100–1400 | 420–700 | 40–50 | 8 | ≈2 h | ≈2 GB |
| 5–8 min | 1650–2200 | 700–1150 | 60–80 | 10–14 | ≈2–3 h | ≈3 GB |
Chapter count follows the content, within limits set by length: under 3 minutes use a single chapter (no chapter cards), 3–5 minutes 3–4 chapters of at least 60 s each, 5–8 minutes 4–6. The progress bar splits evenly across however many chapters the narration declares. A blank line in the narration marks a paragraph, which is also one shot: sentences inside a paragraph are separated by 10 frames, paragraph ends by 30, so the pause lands where the picture changes and every shot holds 1–1.5 s after its last element lands. The finished video runs 5–8% longer than the raw speech by design.
Install
git clone https://github.com/Vincentwei1021/anything2explainer.git
ln -s "$PWD/anything2explainer" ~/.claude/skills/anything2explainer # Claude Code
ln -s "$PWD/anything2explainer" ~/.codex/skills/anything2explainer # Codex
Dependencies:
# Node ≥18 (the template's npm install pulls remotion 4.0.507 / react 19)
brew install ffmpeg # frame extraction / transcoding, required
python3 -m venv ~/.venvs/a2e && source ~/.venvs/a2e/bin/activate
pip install 'edge-tts==7.2.8' numpy pillow scipy # pin edge-tts: it tracks a Microsoft endpoint and breaks across upgrades (7.2.0+ needs word boundaries requested explicitly; the script does)
# only needed for English narration (kokoro-82m runs locally)
pip install kokoro soundfile && brew install espeak-ng
scipy is only used by the QC script frame_metrics.py. The shell scripts are zsh + Python 3, developed and verified on macOS; Linux should work, Windows is untested.
Linux / Raspberry Pi (ARM)
Verified on a Raspberry Pi 5 (ARM64, Python 3.13). Three things differ from macOS:
sudo apt install zsh espeak-ng # scripts are #!/bin/zsh; espeak-ng for kokoro/piper G2P
# Remotion has no linux-arm64 headless browser → point it at system Chromium:
sudo apt install chromium # or chromium-browser
export REMOTION_BROWSER_EXECUTABLE=/usr/bin/chromium # read by template/remotion.config.ts (no-op on macOS)
TTS on Linux/ARM. kokoro (the default English engine) is hard to install on ARM/Python 3.13 (it pins an old numpy and pulls spaCy → blis, which lack aarch64 wheels). Two local engines that install cleanly instead — pass one via TTS_ENGINE:
# kokoro_onnx — natural voice, onnxruntime (no torch/spaCy). Download model + voices from
# github.com/thewh1teagle/kokoro-onnx releases (kokoro-v1.0.onnx, voices-v1.0.bin)
pip install kokoro-onnx
TTS_ENGINE=kokoro_onnx KOKORO_ONNX_MODEL=…/kokoro-v1.0.onnx KOKORO_ONNX_VOICES=…/voices-v1.0.bin \
KOKORO_ONNX_VOICE=am_michael python3 scripts/tts_build.py
# piper — fastest local, robotic; a Pi-native fallback. Voice .onnx from github.com/rhasspy/piper
pip install piper-tts
TTS_ENGINE=piper PIPER_MODEL=…/en_US-ryan-medium.onnx python3 scripts/tts_build.py
The edge engine (natural, free, word-boundary timing) also works on Linux and needs no local model — it's a cloud call to Microsoft: TTS_ENGINE=edge VOICE=en-US-AndrewNeural python3 scripts/tts_build.py.
Usage
In Claude Code or Codex, just say what you want. The skill triggers itself:
Make me an explainer video about vector databases.
讲一下向量数据库，做成一条讲解视频
It then walks the 9 stages in SKILL.md:
- Scaffold the Remotion project from the template.
- Research (1 agent): a sourced research doc with a list of numbers and analogies, every item with a URL.
- Narration & timeline: the script, then TTS voiceover with per-word boundaries turned into a frame-accurate timeline and subtitle table.
- Storyboard: one line per shot with frame range, beat, visuals, motion, hero element and lighting.
- Overlays & primitives: title, chapter cards, HUD, pipeline rail, plus 2–5 topic-specific icons.
- Pilot (1 agent): the first shot group, then a 30-second cut for you to judge the look.
- Parallel build: the remaining groups, 5–7 shots per agent, each writing pure-function Remotion components.
- Render the full film and run quantitative frame metrics.
- QC & fixes: one QC agent per chapter, fix agents per group, re-verification, then delivery notes.
You can also drive the template by hand:
template/scripts/new_project.sh ~/work/my-video myslug
cd ~/work/my-video
# 1. research/调研.md 2. script/narration.txt → python3 scripts/tts_build.py
# 3. script/storyboard_src.md → python3 scripts/render_storyboard.py 4. edit src/config.ts
# 5. src/shots/G1..Gn 6. scripts/preview.sh 30 (first 30 seconds)
# 7. VER=v1 scripts/render.sh + python3 scripts/frame_metrics.py 8. QC → fix → v2/v3
Four checkpoints
The run stops and waits for you at exactly four points instead of ploughing through (details in SKILL.md):
- Length and language: before the script is written. Length decides the line count, shot count and how many agents run in parallel, i.e. how much the film can actually cover; language flips
langinsrc/config.ts, which drives typography, subtitle budgets and the default voice. - Narration sign-off: before voiceover. Once locked, frame numbers are hard-coded into every shot; changing one word re-times the whole film. This is the cheapest place to intervene.
- Voiceover: before TTS runs you get asked whether you have a preferred engine. If not, defaults apply (edge-tts Yunxi for Chinese, kokoro-82m Liam for English). You can also hand over finished audio and fill the per-line timeline yourself.
- First 30 seconds: only the first build group is done, then 30 seconds get rendered for you to judge the look. Fixing the style here costs one group; after the full render it costs every group.
How it compares
| Tool class | What it produces | Where anything2explainer differs |
|---|---|---|
| Generative video models (Sora, Veo, Runway) | Footage synthesized from a prompt | Deterministic code, not pixels. Every number on screen traces to a source URL, and any frame can be fixed by editing one shot file |
| Avatar / presenter tools (HeyGen, Synthesia) | A digital presenter reading a script | No presenter. Motion-graphics diagrams that show the mechanism, with the narration driving the visuals |
| Remotion or Motion Canvas by hand | A programmable video canvas | Ships the method on top of the canvas: research → narration → storyboard → parallel build → QC, with style specs, motion vocabulary and a reference film to match |
| Manim | Python mathematical animations | An agent-driven end-to-end pipeline with TTS-aligned subtitles, chapters and QC; React / TypeScript rather than Python |
FAQ
Which AI coding agents does it work with?
It is written for Claude Code and Codex, and those two are what it has been run with. The skill itself is plain Markdown plus a Remotion project, so any agent that reads SKILL.md-style skill folders and can run shell commands should be able to follow it.
Does it need a GPU? No. Remotion renders through headless Chromium on the CPU. The Chinese default voice (edge-tts) is a cloud call to a Microsoft endpoint; the English default (kokoro-82m) is an 82M-parameter model that runs locally on CPU.
Can I use my own voice or a different TTS?
Yes. Put the finished audio at public/assets/<slug>/audio.wav and fill src/common/timeline.ts and subs.ts by hand (format documented at the top of tts_build.py). Everything downstream is unchanged.
Can I change the visual style?
There is one visual style, on purpose, with a single switch: the backdrop, bg in src/config.ts ('dots' dot-field wave by default, 'stars' star field with fog). To change anything else, edit reference/style-guide.md and src/ui.tsx; the shot code only uses those primitives.
Are the renders reproducible? Yes. Every animation is a pure function of the frame number with seeded randomness, and text fitting is computed rather than measured in the DOM, so re-rendering produces identical frames.
Can I use it commercially? The toolkit is licensed under PolyForm Noncommercial: free for noncommercial use, commercial use requires prior authorization from the author. The videos you make with it are yours. See License.
Does it do vertical (9:16) video? Not currently. The template and every safe-area rule assume 1280×720 landscape.
Which languages?
Chinese and English. Each has its own pacing model, subtitle budget and default voice. Both cuts are embedded at the top of this page; the written paper trail in examples/rag/ is from the Chinese cut.
Repo layout
SKILL.md the process: 9 stages, four checkpoints, quality bar
reference/ specs written for the main session and the agents
style-guide.md safe areas, palette, fonts, primitive catalogue, layout habits
motion-vocabulary.md entrance / emphasis / light / exit / camera formulas and frame counts
composition-and-light.md three size tiers, light follows the hero, set-piece choreography, QC metrics
narration-storyboard.md how to write narration, voiceover params, storyboard tokens, shot pattern table
research-brief.md researcher prompt and fact rules
agent-build-rules.md build-agent protocol
agent-qc-rules.md QC-agent protocol
prompts.md six prompt templates: research / build / QC / fix / recheck / final pass
lessons.md every trap hit across three films, with root causes
template/ the compilable Remotion 4 project (copy it with scripts/new_project.sh)
src/common/ fog, star field, dot-field wave, glitch, easings, subtitles, progress bar, footage layer
src/ui.tsx src/fx.tsx primitives and palette / light, depth and camera primitives
src/overlay/ title, chapter cards, HUD, pipeline rail, ending
scripts/ voiceover, storyboard, stills, test render, 30s preview, full render, QC metrics
public/fonts/ four fonts + their OFL license
examples/rag/ the reference film's full paper trail and rendered frames
examples/contrast/ 6 bad/good frame pairs — the yardstick for composition and light
Acknowledgements
The visual language and the quality bar are inspired by the Douyin creator @图灵宇宙 — black canvas, white line art with purple accents, ultra-bold headline type: that vocabulary was learned from their videos. Everything in this repo is drawn from scratch in code; none of their frames, assets or project files are used. If you feel this crosses a line, please open an issue.
Originality
- Every frame is drawn in code. No frames or clips from existing videos. Optional live-action B-roll must come from royalty-free sources and be logged in a MANIFEST (sha256 / source URL / license / usage).
- Every fact is sourced. Every number, year, organisation and English term shown on screen must trace back to a source URL in that film's research document. Anything unverified stays off the screen and out of the narration.
License
The toolkit: PolyForm Noncommercial 1.0.0 — free for noncommercial use; commercial use requires prior authorization from the author. Videos you make with it are yours.
The four bundled fonts (Noto Sans SC / Orbitron / Exo 2 / Audiowide) are licensed separately under SIL OFL 1.1; see template/public/fonts/LICENSE.md.
Remotion itself has its own license terms for companies — see remotion.dev/license.
Known limits
- Chinese and English are both supported (
lang: 'zh' | 'en'), each with its own pacing, subtitle budget (16 chars / 48 characters per block) and default voice. Both cuts are embedded above; the paper trail inexamples/rag/is from the Chinese cut. One visual style with two backdrops (bg: 'stars' | 'dots'); changing anything else means editingreference/style-guide.md+src/ui.tsx. - Not for: replicating an existing video, talking-head presenter footage, or films that are mostly live action.
- Once the narration is voiced, the words are frozen — shot code hard-codes frame numbers, so a rewrite re-times everything.
- Parallel builds are demanding: several agents bundle Remotion at once, so keep ≥5 GB free; tmux panes are capped, so past ~12 you have to dispatch in waves.
Star History
anything2explainer
English | 简体中文
给一个主题，产出一条带配音的科普讲解视频。 anything2explainer 是一个 Claude Code / Codex skill：输入任意主题，输出一条黑底 MG（motion graphics）风格的讲解视频，带 TTS 配音、字幕和章节进度条，中文或英文都行。画面全部由 Remotion（React + TypeScript）代码绘制，不用素材库，不用视频生成模型，也不使用任何现有视频的帧。
它不是一个 CLI。仓库里装的是让 AI 编程 agent 把片子做出来的整套方法：可编译的 Remotion 模板工程、图元与光效库、配音/分镜/渲染/量化质检工具、风格与动效规范、多 agent 分工协议，以及一条完整样片作为质量标尺。
中文版——《RAG 与知识库》v2，4′54″，44 句 / 1490 字，点阵波幕底（bg: 'dots'），配音走"自带 TTS"路径（火山引擎语音合成 2.0 + 强制对齐）：
https://github.com/user-attachments/assets/5c213990-cbba-439e-8371-fbb3aa348e05
英文版——RAG & Knowledge Bases，5′02″，44 句 / 785 词，kokoro-82m am_liam 自然语速：
https://github.com/user-attachments/assets/e2771c68-a28c-4459-ac5a-a5b685181eeb
两版共用一套分镜和 44 个镜头，英文版按英文配音逐镜头重排帧号。中文原版（4′35″，星点幕底，8 个构建 agent 并行 40 分钟 + 两轮 QC）的全套过程文件在 examples/rag/（调研 → 解说词 → 分镜表 → 镜头源码 → QC 报告 → 交付说明），成片帧在 examples/rag/frames/。
它做什么
- 输入：一个主题（"讲一下向量数据库"），或一篇想改成视频的文章/文档。时长和语言由你定。
- 输出：1280×720 的 H.264 MP4，配音与字幕按词边界对齐，带章节卡、顶部 HUD 和底部章节进度条；同时交付全套过程文件（带出处的调研文档、解说词、分镜表、逐镜头源码、QC 报告）。
- 怎么做：agent 先做带出处的调研，写解说词，生成配音和帧级时间轴，逐镜头写分镜，再派多个构建 agent 并行写 Remotion 组件（一个镜头一个文件）；渲染后由 QC agent 按书面判据逐帧检查，修完再交付。
- 耗时：按时长约 1–3 小时，大部分时间是 agent 并行构建镜头。全程只在四个确认点问你。
成片规格
| 画幅 / 帧率 | 1280×720 @ 30fps，H.264 |
| 时长 | 由你定（见下表），2–8 分钟都能做 |
| 语言 | 中文或英文（src/config.ts 的 lang）；排版、字幕长度预算、配音默认值随它切换 |
| 视觉 | 黑底，幕底二选一：点阵波（默认，移植自 video-talkcraft 的 dot-field-wave），或星点 + 雾底渐变（src/config.ts 的 bg）；白线条图形 + 紫色重点；超粗黑体大字 |
| 常驻层 | 44px 白字黑边字幕、底部章节进度条、顶部胶囊 HUD、可选流程轨、片尾署名 built by Anything2Explainer skill（config.builtBy，设为 '' 去掉） |
| 配音 | 中文 edge-tts zh-CN-YunxiNeural（云希，男声，原速不加速 ≈5.5 字/秒）/ 英文 kokoro-82m am_liam（Liam，男声）；也可用你自己的 TTS 或成品配音 |
时长决定内容丰富程度与全流程规模：
| 时长 | 中文字数 | 英文词数 | 句 / 镜头数 | 构建 agent | 产出耗时 | 磁盘 |
|---|---|---|---|---|---|---|
| 2–3 分钟 | 650–880 | 280–420 | 24–32 | 4–6 | ≈1 小时 | ≈2GB |
| 3–5 分钟（样片档） | 1100–1400 | 420–700 | 40–50 | 8 | ≈2 小时 | ≈2GB |
| 5–8 分钟 | 1650–2200 | 700–1150 | 60–80 | 10–14 | ≈2–3 小时 | ≈3GB |
章数按内容定、受时长约束：<3 分钟单章（不出章节卡），3–5 分钟 3–4 章且每章 ≥60 s，5–8 分钟 4–6 章；进度条按解说词声明的章数等宽分段。解说词用空行分段，一段就是一个镜头：段内句间只隔 10 帧、段末 30 帧，停顿落在画面切换处，每个镜头末拍落位后能停 1–1.5 s 再切；成片比纯语音长 5–8% 是设计内的。
安装
git clone https://github.com/Vincentwei1021/anything2explainer.git
ln -s "$PWD/anything2explainer" ~/.claude/skills/anything2explainer # Claude Code
ln -s "$PWD/anything2explainer" ~/.codex/skills/anything2explainer # Codex
依赖：
# Node ≥18（模板 npm install 会装 remotion 4.0.507 / react 19）
brew install ffmpeg # 抽帧 / 转码，必需
python3 -m venv ~/.venvs/a2e && source ~/.venvs/a2e/bin/activate
pip install 'edge-tts==7.2.8' numpy pillow scipy # 建议固定 edge-tts 版本：它跟着微软端点变，升级常有破坏性（7.2.0 起词边界要显式请求，脚本已处理）
# 只做英文片时再装（kokoro-82m 本地推理）
pip install kokoro soundfile && brew install espeak-ng
scipy 只给质检脚本 frame_metrics.py 用。脚本是 zsh + Python 3，在 macOS 上开发与验证；Linux 应可用，Windows 未测试。
Linux / 树莓派（ARM）
已在树莓派 5（ARM64、Debian trixie、Python 3.13）上跑通。与 macOS 有三处不同：
sudo apt install zsh espeak-ng # 脚本是 #!/bin/zsh；espeak-ng 供 kokoro/piper 的 G2P
# Remotion 没有 linux-arm64 的无头浏览器 → 指向系统 Chromium：
sudo apt install chromium # 或 chromium-browser
export REMOTION_BROWSER_EXECUTABLE=/usr/bin/chromium # 由 template/remotion.config.ts 读取（macOS 上无副作用）
Linux/ARM 上的配音。 默认英文引擎 kokoro 在 ARM/Python 3.13 上很难装：它固定了旧版 numpy（无 aarch64/py3.13 轮子，只能源码编译，会失败），且依赖 spaCy → blis（无 aarch64 轮子、编译不过）。补了两个能干净安装的本地引擎，用 TTS_ENGINE 指定，二者都走既有的“逐字幕块合成”路径：
# kokoro_onnx —— 音色自然，onnxruntime（不依赖 torch/spaCy）。模型与声音库从
# github.com/thewh1teagle/kokoro-onnx 的 releases 下（kokoro-v1.0.onnx、voices-v1.0.bin）
pip install kokoro-onnx
TTS_ENGINE=kokoro_onnx KOKORO_ONNX_MODEL=…/kokoro-v1.0.onnx KOKORO_ONNX_VOICES=…/voices-v1.0.bin \
KOKORO_ONNX_VOICE=am_michael python3 scripts/tts_build.py
# piper —— 最快的本地引擎，音色偏机械，作树莓派原生兜底。语音 .onnx 从 github.com/rhasspy/piper 下
pip install piper-tts
TTS_ENGINE=piper PIPER_MODEL=…/en_US-ryan-medium.onnx python3 scripts/tts_build.py
edge 引擎（自然、免费、有词级边界）在 Linux 上也能用，且不需要本地模型——它是调微软云端接口：TTS_ENGINE=edge VOICE=en-US-AndrewNeural python3 scripts/tts_build.py。
用法
在 Claude Code 或 Codex 里直接说要做什么，skill 会被触发：
讲一下向量数据库，做成一条讲解视频
Make me an explainer video about vector databases.
它会按 SKILL.md 的 9 个阶段走：
- 建项目：从模板复制出 Remotion 工程。
- 调研（1 个 agent）：带出处的调研文档，含数字与比喻清单，每条带 URL。
- 解说词与时间轴：写文案，TTS 配音，按词边界生成帧级时间轴和字幕表。
- 分镜：每镜头一行，写帧区间、节拍、画面、动效、主角与光。
- 覆盖层与图元：片头、章节卡、HUD、流程轨，外加 2–5 个主题图标。
- 打样（1 个 agent）：先做第一组镜头，渲 30 秒样片给你看风格。
- 并行构建：其余各组，每个 agent 5–7 个镜头，写纯函数 Remotion 组件。
- 渲染：整片渲染并跑量化帧指标。
- QC 与修复：每章一个 QC agent，按组派修复 agent，复验后写交付说明。
也可以手动跑模板：
template/scripts/new_project.sh ~/work/my-video myslug
cd ~/work/my-video
# 1. research/调研.md 2. script/narration.txt → python3 scripts/tts_build.py
# 3. script/storyboard_src.md → python3 scripts/render_storyboard.py 4. 改 src/config.ts
# 5. src/shots/G1..Gn 6. scripts/preview.sh 30（前 30 秒样片）
# 7. VER=v1 scripts/render.sh + python3 scripts/frame_metrics.py 8. QC → 修 → v2/v3
四个确认点
流程会在这四处停下来等你回话，不会闷头做完（细节见 SKILL.md）：
- 时长与语言：写文案之前。时长决定句数、镜头数和并行 agent 数，也就决定内容能铺多丰富；语言决定
src/config.ts的lang，进而影响排版、字幕预算和默认音色。 - 解说词定稿：配音之前。定稿后帧号会被每个镜头硬编码，改一个字全片重对位，这是最便宜的干预点。
- 配音：跑 TTS 之前问一句你有没有偏好的 TTS；没有就用默认（中文 edge-tts 云希、英文 kokoro-82m Liam）。也可以直接给成品配音，自己按逐句时间轴填
timeline.ts。 - 前 30 秒样片：只建完第一个构建组就渲 30 秒给你看风格。在这里改一次是 1 个组的成本，整片渲完再改是全部组。
和其他工具的区别
| 工具类型 | 产出什么 | anything2explainer 的不同 |
|---|---|---|
| 视频生成模型（Sora、Veo、可灵、即梦） | 按提示词生成的画面 | 确定性代码而不是像素：画面上每个数字都能追溯到来源 URL，任何一帧都能通过改一个镜头文件修好 |
| 数字人 / 口播工具（HeyGen、Synthesia） | 一个数字人读稿 | 没有主播；用 MG 图形把机制画出来，解说词驱动画面 |
| 直接手写 Remotion / Motion Canvas | 一块可编程的视频画布 | 在画布之上给出整套方法：调研 → 解说词 → 分镜 → 并行构建 → QC，附风格规范、动效词表和一条可对标的样片 |
| Manim | Python 数学动画 | agent 驱动的端到端流水线，字幕按 TTS 对齐，带章节与 QC；技术栈是 React / TypeScript 而不是 Python |
常见问题
支持哪些 AI 编程 agent？
为 Claude Code 和 Codex 编写，也只在这两个上跑过。skill 本身就是 Markdown 加一个 Remotion 工程，任何能读 SKILL.md 式 skill 目录、能执行 shell 命令的 agent 理论上都能照着做。
需要 GPU 吗？ 不需要。Remotion 用无头 Chromium 在 CPU 上渲染。中文默认配音 edge-tts 是调微软云端接口；英文默认 kokoro-82m 是 8200 万参数的小模型，本地 CPU 就能跑。
能用自己的声音或别的 TTS 吗？
可以。把成品音频放到 public/assets/<slug>/audio.wav，按 tts_build.py 文件头的格式手填 src/common/timeline.ts 和 subs.ts，后续流程不变。
能换视觉风格吗？
只做这一种风格，是有意为之，唯一的开关是幕底：src/config.ts 的 bg（默认 'dots' 点阵波，可选 'stars' 星点雾底）。其他要换就改 reference/style-guide.md 和 src/ui.tsx，镜头代码只用这些图元。
渲染结果可复现吗？ 可以。所有动画都是帧号的纯函数，随机数带种子，文字排版靠计算而不测 DOM，重渲一遍帧完全一样。
能商用吗？ 工具包本身是 PolyForm Noncommercial 许可：非商业使用免费，商业使用需事先获得作者授权。用它做出来的视频归你自己。见许可。
能做竖屏（9:16）吗？ 目前不能。模板和全部安全区规则都按 1280×720 横屏设计。
支持哪些语言？
中文和英文。各有自己的语速模型、字幕预算与默认音色。两版成片都嵌在本页顶部；examples/rag/ 里的过程文件是中文版的。
仓库结构
SKILL.md 流程主文档：9 个阶段、四个确认点、质量标尺
reference/ 写给主会话与 agent 的规范
style-guide.md 安全区、调色板、字体、图元目录、版式规律
motion-vocabulary.md 入场/强调/光效/离场/运镜的公式与帧数
composition-and-light.md 主体尺寸三档、光跟主角、高光时刻编排、量化判据
narration-storyboard.md 解说词写法、配音参数、分镜令牌、镜头设计模式表
research-brief.md 研究员 prompt 与事实规则
agent-build-rules.md 构建 agent 协议
agent-qc-rules.md QC agent 协议
prompts.md 研究/构建/QC/修复/复验/终检六种 prompt 模板
lessons.md 三部片子踩过的坑与根因
template/ 可编译的 Remotion 4 项目（用 scripts/new_project.sh 复制）
src/common/ 雾底、星点、点阵波、glitch、缓动、字幕、进度条、实拍层
src/ui.tsx src/fx.tsx 图元与调色板 / 光效·纵深·运镜图元
src/overlay/ 片头、章节卡、HUD、流程轨、片尾
scripts/ 配音、分镜、still、测渲、前 N 秒样片、整片渲染、量化质检
public/fonts/ 四款字体 + OFL 许可
examples/rag/ 样片全套过程文件与成片帧
examples/contrast/ 6 组正例/反例帧对照（构图与光的标尺）
致谢
视觉风格的灵感与标尺来自抖音创作者 @图灵宇宙 的科普视频——黑底、白线条配紫色重点、超粗黑体大字这套语言是从他的片子里学来的。本项目所有画面均由代码原创绘制，不使用其任何帧、素材或工程文件；如有不妥请开 issue 告知。
原创性
- 画面全部代码绘制，不使用任何现有视频的帧或片段；可选的实拍 B-roll 只允许免版权来源，并要求登记 MANIFEST（sha256 / 来源 URL / 许可 / 用途）。
- 事实有出处：画面上出现的每个数字、年份、机构、英文术语都必须能在该片的调研文档里找到来源 URL，没核实的不上画面也不进配音。
许可
工具包本身：PolyForm Noncommercial 1.0.0——非商业使用免费，商业使用需事先获得作者授权。用它做出来的视频归你自己。
模板内四款字体（Noto Sans SC / Orbitron / Exo 2 / Audiowide）按 SIL OFL 1.1 单独授权，版权与许可全文见 template/public/fonts/LICENSE.md。
Remotion 自身对公司用户另有授权要求，见 remotion.dev/license。
已知限制
- 中英文都支持（
lang: 'zh' | 'en'），各有自己的语速、字幕块预算（每块 16 字 / 48 字符）与默认音色。两版成片都嵌在上方；examples/rag/的过程文件是中文版的。只做这一种视觉风格，幕底二选一（bg: 'stars' | 'dots'），其他要换就改reference/style-guide.md+src/ui.tsx。 - 不适用：复刻某条现有视频、真人口播、以实拍为主的片子。
- 解说词一旦配音定稿就不能改词（镜头代码里硬编码帧号），改词等于全片重对位。
- 并行构建对机器有要求：多个 agent 同时跑 Remotion bundle，建议预留 ≥5GB 磁盘；tmux pane 有上限，超过 12 个要分波派。