Communitygithub.com

inference-sh/skills (AI 行銷影片製作)

使用 Veo、Seedance、Wan、FLUX 等模型建立專業 AI 行銷影片,涵蓋廣告、促銷、產品發布與品牌內容。

skills (AI 行銷影片製作) 是什麼?

AI 行銷影片製作技能專為行銷人員與開發者設計,能透過 **inference.sh** CLI 生成專業品質的影片廣告。它支援多種影片類型(產品展示、見證、解說、社群廣告與品牌影片),並適用於 Facebook、YouTube、Instagram 與 TikTok 等平台。其核心運作方式為透過 `belt` CLI 呼叫多個 AI 模型:使用 Google Veo、ByteDance Seedance、Wan 與 FLUX 生成視覺內容,再用 Kokoro TTS 生成旁白,最後藉由媒體合併器 (infsh/media-merger) 與音訊合併器 (infsh/video-audio-merger) 完成後製。內建影片廣告範本(如 30 秒產品廣告、Instagram/TikTok 15 秒短廣告、解說影片)及 A/B 測試變體腳本,方便快速迭代。此外,它提供各平台最適規格的指引(如 Facebook 1:1 方型、YouTube 16:9 前置廣告),以及最佳實踐(前 3 秒鉤子、無聲播放輔助字幕、明確 CTA)。總而言之,這是一套從腳本撰寫、視覺生成、配音到最終產出一站式完成的 AI 驅動行銷影片管線。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/inference-sh/skills/tree/HEAD/guides/video/ai-marketing-videos

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

預覽

來自技能 README

AI 行銷影片

說明文件

安裝 belt CLI 技能: npx skills add belt-sh/cli

AI 行銷影片

透過 inference.sh CLI 建立專業行銷影片。

AI 行銷影片

快速開始

需要 inference.sh CLI (belt)。安裝說明

belt login

# 生成一個產品促銷影片
belt app run google/veo-3-1-fast --input '{
  "prompt": "Sleek product reveal video, smartphone emerging from light particles, premium tech aesthetic, commercial quality"
}'

廣告影片類型

類型長度平台
片頭廣告6 秒YouTube
短廣告15 秒Instagram、Facebook
標準廣告30 秒YouTube、電視
解說影片60-90 秒網站、YouTube
產品展示30-60 秒所有平台

行銷影片範本

產品發布

# 戲劇性產品揭曉
belt app run google/veo-3-1 --input '{
  "prompt": "Cinematic product launch video, premium tech device floating in space, dramatic lighting, particles and light effects, Apple-style reveal, commercial quality"
}'

品牌故事

# 情感品牌敘事
belt app run google/veo-3-1 --input '{
  "prompt": "Brand story video showing diverse people connecting through technology, warm color grading, lifestyle montage, emotional and inspiring, commercial"
}'

功能亮點

# 聚焦特定功能
belt app run bytedance/seedance-2-0 --input '{
  "prompt": "Close-up product feature demonstration, hands interacting with device, clean background, informative, tech commercial style",
  "generate_audio": true
}'

見證風格

# 人物訪談見證
belt app run google/veo-3-1-fast --input '{
  "prompt": "Customer testimonial style video, person speaking to camera, neutral office background, professional lighting, authentic feel"
}'

前後對比

# 轉變揭曉
belt app run google/veo-3-1-fast --input '{
  "prompt": "Before and after transformation video, split screen transition, dramatic reveal, satisfying comparison, commercial style"
}'

完整廣告工作流程

30 秒產品廣告

# 1. 開場鉤子(0-3 秒)
belt app run google/veo-3-1-fast --input '{
  "prompt": "Attention-grabbing opening, product silhouette in dramatic lighting, building anticipation"
}' > hook.json

# 2. 問題陳述(3-8 秒)
belt app run google/veo-3-1-fast --input '{
  "prompt": "Frustrated person dealing with common problem, relatable everyday situation, documentary style"
}' > problem.json

# 3. 解決方案揭曉(8-15 秒)
belt app run google/veo-3-1-fast --input '{
  "prompt": "Product reveal with features highlighted, clean demonstration, solving the problem shown before"
}' > solution.json

# 4. 好處展示(15-25 秒)
belt app run google/veo-3-1-fast --input '{
  "prompt": "Happy customer using product, lifestyle integration, multiple quick cuts showing benefits"
}' > benefits.json

# 5. 行動呼籲(25-30 秒)
belt app run google/veo-3-1-fast --input '{
  "prompt": "Product hero shot with space for text overlay, professional lighting, commercial ending"
}' > cta.json

# 6. 生成旁白
belt app run falai/kokoro-tts --input '{
  "prompt": "Tired of [problem]? Introducing [Product]. [Key benefit 1]. [Key benefit 2]. [Key benefit 3]. Get yours today.",
  "voice": "af_nicole"
}' > voiceover.json

# 7. 合併所有片段與旁白
belt app run infsh/media-merger --input '{
  "media_files": [
    {"file": "<hook>", "transition_type": "crossfade"},
    {"file": "<problem>", "transition_type": "crossfade"},
    {"file": "<solution>", "transition_type": "crossfade"},
    {"file": "<benefits>", "transition_type": "crossfade"},
    {"file": "<cta>", "transition_type": "crossfade"}
  ]
}' > merged.json

belt app run infsh/video-audio-merger --input '{
  "video_file": "<merged-url>",
  "audio_file": "<voiceover>"
}'

Instagram/TikTok 廣告(15 秒)

# 直式格式,快節奏
belt app run google/veo-3-1-fast --input '{
  "prompt": "Fast-paced product showcase, vertical 9:16, quick cuts, trending style, hook in first 2 seconds, satisfying visually, Gen-Z aesthetic"
}'

# 加入流行音樂
belt app run infsh/video-audio-merger --input '{
  "video_file": "<video>",
  "audio_file": "https://trending-music.mp3"
}'

解說影片

# 1. 編寫腳本
belt app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Write a 60-second explainer video script for a SaaS product. Include: hook, problem, solution, 3 key features, social proof, CTA. Make it conversational."
}' > script.json

# 2. 為每個章節生成視覺
SECTIONS=("hook" "problem" "solution" "feature1" "feature2" "feature3" "social_proof" "cta")

for section in "${SECTIONS[@]}"; do
  belt app run google/veo-3-1-fast --input "{
    \"prompt\": \"Explainer video scene for $section, motion graphics style, clean modern aesthetic, SaaS product\"
  }" > "$section.json"
done

# 3. 生成專業旁白
belt app run falai/kokoro-tts --input '{
  "prompt": "<full-script>",
  "voice": "am_michael"
}' > voiceover.json

# 4. 組合最終影片
belt app run infsh/media-merger --input '{
  "media_files": [
    {"file": "<hook>", "transition_type": "crossfade"},
    {"file": "<problem>", "transition_type": "crossfade"},
    {"file": "<solution>", "transition_type": "crossfade"}
  ]
}' > merged.json

belt app run infsh/video-audio-merger --input '{
  "video_file": "<merged-url>",
  "audio_file": "<voiceover>"
}'

各平台專屬格式

Facebook/Instagram 動態牆

belt app run google/veo-3-1-fast --input '{
  "prompt": "Square format product video 1:1, eye-catching visuals, works without sound, text-friendly, scroll-stopping"
}'

YouTube 前置廣告

belt app run google/veo-3-1-fast --input '{
  "prompt": "YouTube ad style, skip button awareness (hook in 5 seconds), 16:9, professional commercial quality"
}'

LinkedIn

belt app run google/veo-3-1-fast --input '{
  "prompt": "Professional B2B product video, corporate style, clean and modern, business audience, subtle motion"
}'

TikTok/Reels

belt app run google/veo-3-1-fast --input '{
  "prompt": "TikTok native style ad, vertical 9:16, raw authentic feel, not overly polished, trendy, user-generated content aesthetic"
}'

廣告創意最佳實務

鉤子公式(前 3 秒)

belt app run google/veo-3-1-fast --input '{
  "prompt": "Opening hook: [choose one]
  - Surprising visual transformation
  - Bold statement text animation
  - Relatable problem scenario
  - Curiosity gap visual
  - Satisfying action"
}'

視覺層次

  1. 產品主角 - 清晰、突出
  2. 好處 - 以圖像呈現,而非僅文字
  3. 社交證明 - 可見的客戶推薦/數據
  4. 行動呼籲 - 為文字疊加預留清晰空間

聲音設計

# 加入合適的音樂
belt app run infsh/ai-music --input '{
  "prompt": "Upbeat commercial background music, modern, energetic, 30 seconds"
}' > music.json

belt app run infsh/video-audio-merger --input '{
  "video_file": "<ad-video>",
  "audio_file": "<music>"
}'

A/B 測試變體

# 生成多個創意變體
HOOKS=(
  "Problem-focused opening"
  "Product reveal opening"
  "Testimonial opening"
  "Statistic opening"
)

for hook in "${HOOKS[@]}"; do
  belt app run google/veo-3-1-fast --input "{
    \"prompt\": \"Marketing video with $hook, professional commercial quality\"
  }" > "variant_${hook// /_}.json"
done

廣告影片檢查清單

  • 前 3 秒即出現鉤子
  • 無聲播放也可理解(字幕/文字)
  • 產品清晰可見
  • 以好處為核心的訊息
  • 單一明確的行動呼籲
  • 符合平台的長寬比
  • 品牌一致性
  • 針對行動裝置最佳化

相關技能

# 影片生成
npx skills add inference-sh/skills@ai-video-generation

# 縮圖圖片生成
npx skills add inference-sh/skills@ai-image-generation

# 旁白文字轉語音
npx skills add inference-sh/skills@text-to-speech

# 社群媒體內容
npx skills add inference-sh/skills@ai-social-media-content

# 完整平台技能
npx skills add inference-sh/skills@infsh-cli

瀏覽所有應用程式:belt app list

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

相關技能