explainer-video-guide

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Explainer Video Guide

解说视频制作指南

Create explainer videos from script to final cut via inference.sh CLI.
通过inference.sh CLI工具完成从脚本到最终剪辑的解说视频制作。

Quick Start

快速开始

bash
curl -fsSL https://cli.inference.sh | sh && infsh login
bash
curl -fsSL https://cli.inference.sh | sh && infsh login

Generate a scene for an explainer

Generate a scene for an explainer

infsh app run google/veo-3-1-fast --input '{ "prompt": "Clean motion graphics style animation, abstract data flowing between connected nodes, blue and white color scheme, professional corporate aesthetic, smooth transitions" }'
undefined
infsh app run google/veo-3-1-fast --input '{ "prompt": "Clean motion graphics style animation, abstract data flowing between connected nodes, blue and white color scheme, professional corporate aesthetic, smooth transitions" }'
undefined

Script Formulas

脚本公式

Problem-Agitate-Solve (PAS) — 60 seconds

问题-激化-解决(PAS)——60秒

SectionDurationContentWord Count
Problem10sState the pain point the viewer has~25 words
Agitate10sShow why it's worse than they think~25 words
Solution15sIntroduce your product/idea~35 words
How It Works20sShow 3 key steps or features~50 words
CTA5sOne clear next action~12 words
部分时长内容字数
问题10秒点明观众面临的痛点~25词
激化10秒说明问题比他们想象的更严重~25词
解决方案15秒介绍你的产品/创意~35词
工作原理20秒展示3个关键步骤或功能~50词
行动号召(CTA)5秒清晰的下一步行动~12词

Before-After-Bridge (BAB) — 90 seconds

过去-现在-桥梁(BAB)——90秒

SectionDurationContent
Before15sShow the current frustrating state
After15sShow the ideal outcome
Bridge40sExplain how your product gets them there
Social Proof10sQuick stat or testimonial
CTA10sClear next step
部分时长内容
过去15秒展示当前令人沮丧的状态
现在15秒展示理想的结果
桥梁40秒说明你的产品如何帮助他们实现转变
社交证明10秒快速展示数据或客户证言
行动号召(CTA)10秒清晰的下一步行动

Feature Spotlight — 30 seconds (social)

功能亮点——30秒(社交平台)

SectionDurationContent
Hook3sSurprising fact or question
Feature15sShow one feature solving one problem
Result7sThe outcome/benefit
CTA5sTry it / Learn more
部分时长内容
钩子3秒惊人事实或问题
功能15秒展示一个功能解决一个问题
结果7秒成果/收益
行动号召(CTA)5秒立即试用 / 了解更多

Pacing Rules

节奏规则

Content TypeWords Per MinuteNotes
Standard narration150 wpmConversational pace
Complex/technical120 wpmAllow processing time
Energetic/social170 wpmFaster for short-form
Children's content100 wpmClear and slow
Key rule: 1 scene per key message. Don't pack multiple ideas into one visual.
内容类型每分钟字数注意事项
标准旁白150词/分钟口语化节奏
复杂/技术内容120词/分钟留足理解时间
活力/社交内容170词/分钟短视频节奏更快
儿童内容100词/分钟清晰缓慢
核心规则: 每个关键信息对应一个场景。不要在一个视觉画面中塞入多个想法。

Scene Duration Guidelines

场景时长指南

  • Establishing shot: 3-5 seconds
  • Feature demonstration: 5-8 seconds
  • Text/stat on screen: 3-4 seconds (must be readable)
  • Transition: 0.5-1 second
  • CTA screen: 3-5 seconds
  • 开场镜头:3-5秒
  • 功能演示:5-8秒
  • 屏幕文本/数据:3-4秒(必须清晰可读)
  • 转场:0.5-1秒
  • 行动号召画面:3-5秒

Visual Production

视觉制作

Scene Types

场景类型

bash
undefined
bash
undefined

Product in context

Product in context

infsh app run google/veo-3-1-fast --input '{ "prompt": "Clean product demonstration video, hands typing on a laptop showing a dashboard interface, bright modern office, soft natural lighting, professional" }'
infsh app run google/veo-3-1-fast --input '{ "prompt": "Clean product demonstration video, hands typing on a laptop showing a dashboard interface, bright modern office, soft natural lighting, professional" }'

Abstract concept visualization

Abstract concept visualization

infsh app run bytedance/seedance-1-5-pro --input '{ "prompt": "Abstract motion graphics, colorful data streams connecting floating geometric shapes, smooth fluid animation, dark background with glowing elements, tech aesthetic" }'
infsh app run bytedance/seedance-1-5-pro --input '{ "prompt": "Abstract motion graphics, colorful data streams connecting floating geometric shapes, smooth fluid animation, dark background with glowing elements, tech aesthetic" }'

Lifestyle/outcome shot

Lifestyle/outcome shot

infsh app run google/veo-3-1-fast --input '{ "prompt": "Happy person relaxing on couch with laptop, smiling at screen, bright airy living room, warm afternoon light, satisfied customer feeling, lifestyle commercial style" }'
infsh app run google/veo-3-1-fast --input '{ "prompt": "Happy person relaxing on couch with laptop, smiling at screen, bright airy living room, warm afternoon light, satisfied customer feeling, lifestyle commercial style" }'

Before/after comparison

Before/after comparison

infsh app run falai/flux-dev-lora --input '{ "prompt": "Split screen comparison, left side cluttered messy desk with papers and stress, right side clean organized minimalist workspace, dramatic difference, clean design" }'
undefined
infsh app run falai/flux-dev-lora --input '{ "prompt": "Split screen comparison, left side cluttered messy desk with papers and stress, right side clean organized minimalist workspace, dramatic difference, clean design" }'
undefined

Image-to-Video for Scenes

图片转视频制作场景

bash
undefined
bash
undefined

Generate a still frame first

Generate a still frame first

infsh app run falai/flux-dev-lora --input '{ "prompt": "Professional workspace with glowing holographic interface, futuristic but clean, blue accent lighting" }'
infsh app run falai/flux-dev-lora --input '{ "prompt": "Professional workspace with glowing holographic interface, futuristic but clean, blue accent lighting" }'

Animate it

Animate it

infsh app run falai/wan-2-5-i2v --input '{ "prompt": "Gentle camera push in, holographic elements subtly floating and rotating, soft ambient light shifts", "image": "path/to/workspace-still.png" }'
undefined
infsh app run falai/wan-2-5-i2v --input '{ "prompt": "Gentle camera push in, holographic elements subtly floating and rotating, soft ambient light shifts", "image": "path/to/workspace-still.png" }'
undefined

Voiceover Production

旁白制作

Script Writing Tips

脚本撰写技巧

  • Short sentences. Max 15 words per sentence.
  • Active voice. "You can track your data" not "Your data can be tracked."
  • Conversational tone. Read it aloud — if it sounds stiff, rewrite.
  • One idea per sentence. One sentence per visual beat.
  • 短句。每句最多15词。
  • 主动语态。用"你可以追踪数据"而非"数据可以被你追踪"。
  • 口语化语气。大声朗读——如果听起来生硬,就重写。
  • 每句一个想法。每个视觉节拍对应一句话。

Generating Voiceover

生成旁白

bash
undefined
bash
undefined

Professional narration with Dia TTS

Professional narration with Dia TTS

infsh app run falai/dia-tts --input '{ "prompt": "[S1] Tired of spending hours on reports that nobody reads? There is a better way. Meet DataFlow. It turns your raw data into visual stories... in seconds. Just connect your source, pick a template, and share. Try DataFlow free today." }'
undefined
infsh app run falai/dia-tts --input '{ "prompt": "[S1] Tired of spending hours on reports that nobody reads? There is a better way. Meet DataFlow. It turns your raw data into visual stories... in seconds. Just connect your source, pick a template, and share. Try DataFlow free today." }'
undefined

Pacing Control in TTS

文本转语音(TTS)节奏控制

TechniqueEffectExample
Period
.
Medium pause"This changes everything. Here's how."
Ellipsis
...
Long pause (dramatic)"And the result... was incredible."
Comma
,
Short pause"Fast, simple, powerful."
Exclamation
!
Emphasis/energy"Start building today!"
Question
?
Rising intonation"What if there was a better way?"
技巧效果示例
句号
.
中等停顿"这彻底改变了一切。以下是方法。"
省略号
...
长停顿(戏剧性)"而结果...令人难以置信。"
逗号
,
短停顿"快速、简单、强大。"
感叹号
!
强调/活力"今天就开始构建!"
问号
?
升调"如果有更好的方法呢?"

Music & Audio

音乐与音频

Background Music Guidelines

背景音乐指南

  • Volume: 20-30% under narration (duck 6-12dB when voice plays)
  • Style: match the brand tone (corporate = ambient electronic, startup = upbeat indie)
  • Structure: intro swell (first 3s) -> subtle loop under narration -> swell at CTA
  • No vocals: instrumental only under narration
bash
undefined
  • 音量: 比旁白低20-30%(旁白播放时降低6-12分贝)
  • 风格: 匹配品牌调性(企业=氛围电子乐,初创公司=欢快独立音乐)
  • 结构: 开场渐强(前3秒)-> 旁白下的轻柔循环 -> 行动号召时渐强
  • 无 vocals: 旁白下仅用纯音乐
bash
undefined

Generate background music

Generate background music

infsh app run <music-gen-app> --input '{ "prompt": "upbeat corporate background music, modern electronic, 90 BPM, positive and professional, no vocals, suitable for product explainer video" }'
undefined
infsh app run <music-gen-app> --input '{ "prompt": "upbeat corporate background music, modern electronic, 90 BPM, positive and professional, no vocals, suitable for product explainer video" }'
undefined

Assembly Pipeline

组装工作流

Full Production Workflow

完整制作流程

bash
undefined
bash
undefined

1. Generate voiceover

1. Generate voiceover

infsh app run falai/dia-tts --input '{ "prompt": "[S1] Your script here..." }'
infsh app run falai/dia-tts --input '{ "prompt": "[S1] Your script here..." }'

2. Generate scene visuals (in parallel)

2. Generate scene visuals (in parallel)

infsh app run google/veo-3-1-fast --input '{"prompt": "scene 1 description"}' --no-wait infsh app run google/veo-3-1-fast --input '{"prompt": "scene 2 description"}' --no-wait infsh app run google/veo-3-1-fast --input '{"prompt": "scene 3 description"}' --no-wait
infsh app run google/veo-3-1-fast --input '{"prompt": "scene 1 description"}' --no-wait infsh app run google/veo-3-1-fast --input '{"prompt": "scene 2 description"}' --no-wait infsh app run google/veo-3-1-fast --input '{"prompt": "scene 3 description"}' --no-wait

3. Merge scenes into sequence

3. Merge scenes into sequence

infsh app run infsh/media-merger --input '{ "media": ["scene1.mp4", "scene2.mp4", "scene3.mp4"] }'
infsh app run infsh/media-merger --input '{ "media": ["scene1.mp4", "scene2.mp4", "scene3.mp4"] }'

4. Add voiceover to video

4. Add voiceover to video

infsh app run infsh/video-audio-merger --input '{ "video": "merged-scenes.mp4", "audio": "voiceover.mp3" }'
infsh app run infsh/video-audio-merger --input '{ "video": "merged-scenes.mp4", "audio": "voiceover.mp3" }'

5. Add captions

5. Add captions

infsh app run infsh/caption-videos --input '{ "video": "final-with-audio.mp4", "caption_file": "captions.srt" }'
undefined
infsh app run infsh/caption-videos --input '{ "video": "final-with-audio.mp4", "caption_file": "captions.srt" }'
undefined

Video Length by Format

不同格式的视频时长

FormatLengthPlatform
Social teaser15-30sTikTok, Instagram Reels, YouTube Shorts
Product demo60-90sWebsite, landing page
Feature explainer90-120sYouTube, email
Tutorial/walkthrough2-5minYouTube, help center
Investor pitch video2-3minPitch deck supplement
格式时长平台
社交预告15-30秒TikTok、Instagram Reels、YouTube Shorts
产品演示60-90秒官网、着陆页
功能解说90-120秒YouTube、邮件
教程/操作演示2-5分钟YouTube、帮助中心
投资者推介视频2-3分钟推介补充材料

Transition Types

转场类型

TransitionWhen to UseEffect
CutDefault between related scenesClean, professional
Dissolve/CrossfadeTime passing, mood shiftSoft, contemplative
WipeNew topic or sectionClear separation
Zoom/PushDrilling into detailFocus attention
Match cutVisual similarity between scenesClever, memorable
转场使用场景效果
硬切相关场景间的默认转场简洁、专业
溶解/交叉淡入淡出时间流逝、情绪转变柔和、沉思
划像新主题或章节清晰分隔
缩放/推进深入细节聚焦注意力
匹配剪辑场景间视觉相似巧妙、难忘

Common Mistakes

常见错误

MistakeProblemFix
Script too wordyVoiceover rushed, viewer overwhelmedCut to 150 wpm max
No hook in first 3sViewers leave immediatelyStart with the problem or surprising stat
Visuals lag narrationConfusing disconnectVisuals should match or slightly precede words
Background music too loudCan't hear narrationDuck music 6-12dB under voice
No captions85% of social video watched silentAlways add captions
Too many ideasViewer retains nothingOne core message per video
错误问题解决方法
脚本过于冗长旁白仓促,观众不堪重负最多保留150词/分钟
前3秒无钩子观众立即离开从问题或惊人数据开始
视觉滞后于旁白混乱脱节视觉应匹配或略早于旁白内容
背景音乐音量过大听不到旁白旁白播放时将音乐降低6-12分贝
无字幕85%的社交视频静音观看始终添加字幕
想法过多观众什么都记不住每个视频一个核心信息

Related Skills

相关技能

bash
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@text-to-speech
npx skills add inference-sh/skills@prompt-engineering
Browse all apps:
infsh app list
bash
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@text-to-speech
npx skills add inference-sh/skills@prompt-engineering
浏览所有应用:
infsh app list