Install the belt CLI skill: npx skills add belt-sh/cli
Video Ad Specs
Create platform-specific video ads via inference.sh CLI.
Quick Start
Requires inference.sh CLI (belt). Install instructions
belt login
# Generate a vertical video ad scene
belt app run bytedance/seedance-2-0 --input '{
"prompt": "vertical video, person excitedly unboxing a product, clean modern room, bright natural lighting, social media ad style, authentic feeling",
"ratio": "9:16",
"generate_audio": true
}'
Platform Specifications
TikTok
| Spec |
Value |
| Aspect ratio |
9:16 (vertical) |
| Resolution |
1080 x 1920 px |
| Duration |
5-60 seconds (15-30s recommended) |
| File size |
Max 500 MB |
| Format |
MP4, MOV |
| Sound |
On by default (design with sound) |
| Text safe zone |
150px from all edges |
| Hook window |
1 second — first frame must grab attention |
Instagram Reels
| Spec |
Value |
| Aspect ratio |
9:16 (vertical) |
| Resolution |
1080 x 1920 px |
| Duration |
Up to 90 seconds (15-30s for ads) |
| Cover image |
Separate upload, shows in grid |
| Sound |
On by default |
| Caption area |
Bottom 20% reserved for text overlay |
Instagram Stories
| Spec |
Value |
| Aspect ratio |
9:16 |
| Resolution |
1080 x 1920 px |
| Duration |
Up to 15 seconds per segment |
| Swipe-up/Link |
Available for ads |
| Top/bottom |
14% top and 20% bottom = unsafe for key content |
YouTube
| Format |
Aspect |
Duration |
Skip |
| Bumper |
16:9 |
6 seconds exactly |
Non-skippable |
| Non-skippable |
16:9 |
15 seconds |
Non-skippable |
| Skippable (TrueView) |
16:9 |
Any length |
Skip after 5 seconds |
| Shorts |
9:16 |
Up to 60 seconds |
N/A |
Resolution: 1920 x 1080 (16:9) or 1080 x 1920 (Shorts)
Facebook Feed
| Spec |
Value |
| Aspect ratio |
1:1 (square) or 4:5 (recommended for mobile) |
| Resolution |
1080 x 1080 or 1080 x 1350 |
| Duration |
Up to 240 min (15-30s recommended) |
| Autoplay |
Silent — captions are essential |
| Sound |
85% of Facebook video is watched without sound |
LinkedIn
| Spec |
Value |
| Aspect ratio |
1:1 or 16:9 |
| Resolution |
1080 x 1080 or 1920 x 1080 |
| Duration |
3 seconds to 10 minutes (15-30s for ads) |
| Tone |
Professional |
| Autoplay |
Silent in feed |
AIDA Framework for Video Ads
| Phase |
Time |
Goal |
Technique |
| Attention |
0-3s |
Stop the scroll |
Pattern interrupt, bold visual, question |
| Interest |
3-10s |
Keep watching |
State the problem, show relevance |
| Desire |
10-20s |
Want the solution |
Show the product/outcome, social proof |
| Action |
Final 3-5s |
Click/buy/sign up |
Clear CTA, urgency, offer |
Hook Techniques (First 3 Seconds)
| Technique |
Example |
| Bold statement |
"This tool replaced my entire marketing team" |
| Question |
"Why are you still doing this manually?" |
| Surprising visual |
Unexpected transformation, before/after reveal |
| Pattern interrupt |
Start mid-action, unusual angle, bright color |
| Social proof |
"2 million people switched to this" |
| Pain point |
"If you hate [common frustration], watch this" |
Creating Video Ads
Vertical (TikTok, Reels, Stories, Shorts)
# Hook scene (0-3s)
belt app run google/veo-3-1-fast --input '{
"prompt": "vertical 9:16 video, close-up of hands struggling with tangled cables and messy desk, frustrated energy, shaky handheld camera, authentic social media style, bright lighting"
}'
# Solution reveal (3-15s)
belt app run bytedance/seedance-2-0 --input '{
"prompt": "vertical video, smooth product reveal, clean wireless charging station on minimalist desk, satisfying organization transformation, bright modern room, social media ad aesthetic",
"ratio": "9:16",
"generate_audio": true
}'
# Add voiceover
belt app run falai/dia-tts --input '{
"prompt": "[S1] Stop wasting time with this mess. This one product changed my entire setup. Everything charges. Everything is organized. Link in bio."
}'
# Merge video + audio
belt app run infsh/video-audio-merger --input '{
"video": "solution-reveal.mp4",
"audio": "voiceover.mp3"
}'
# Add captions (critical for silent autoplay)
belt app run infsh/caption-videos --input '{
"video": "ad-with-audio.mp4",
"caption_file": "captions.srt"
}'
Square (Facebook, LinkedIn Feed)
belt app run google/veo-3-1-fast --input '{
"prompt": "square 1:1 video, professional person at desk discovering a new software tool, laptop screen showing clean dashboard, natural office lighting, corporate commercial style, satisfied expression"
}'
YouTube Bumper (6 Seconds)
# 6-second bumper: one message, one visual, one CTA
belt app run google/veo-3-1-fast --input '{
"prompt": "6 second product ad, quick montage of a sleek app being used on phone, fast cuts, modern, energetic, brand logo reveal at end, punchy and dynamic, wide 16:9"
}'
# Keep it tight
belt app run falai/dia-tts --input '{
"prompt": "[S1] Your reports. Automated. Try DataFlow free."
}'
Captions Are Mandatory
85% of Facebook and 40%+ of Instagram video is watched on mute.
Caption Best Practices
| Rule |
Reason |
| Always add captions |
Silent viewing is the default on most platforms |
| Large, readable font |
Small text is invisible on mobile |
| High contrast |
White text with dark outline/background |
| Centered or bottom-third |
Standard viewing position |
| Max 2 lines at a time |
More text = can't be read fast enough |
| Key words in bold/color |
Draws eye to important words |
# Generate captions from audio
# (create SRT file from your script, then burn in)
belt app run infsh/caption-videos --input '{
"video": "ad-video.mp4",
"caption_file": "ad-captions.srt"
}'
Ad Structure Templates
Testimonial Ad (15-30s)
| Time |
Content |
| 0-3s |
Customer states the problem they had |
| 3-15s |
How they discovered and tried the product |
| 15-25s |
The specific result they achieved |
| 25-30s |
Product name + CTA |
Demo Ad (15-30s)
| Time |
Content |
| 0-3s |
The problem (text or visual) |
| 3-20s |
Product demo showing the solution |
| 20-25s |
Key result/benefit |
| 25-30s |
CTA + offer |
Before/After Ad (15s)
| Time |
Content |
| 0-3s |
"Before" state (messy, slow, frustrating) |
| 3-5s |
Transition / product introduction |
| 5-12s |
"After" state (clean, fast, satisfying) |
| 12-15s |
CTA |
Common Mistakes
| Mistake |
Problem |
Fix |
| No hook in first 1-3s |
Viewer scrolls past |
Open with pattern interrupt |
| Landscape video on TikTok/Reels |
Letterboxed, looks amateur |
Use 9:16 for vertical platforms |
| No captions |
Most viewers watch silent |
Always add captions |
| CTA too late |
Viewers already left |
Clear CTA within last 5 seconds |
| Too long for platform |
Forced skip or dropout |
Match platform duration norms |
| Same ad for all platforms |
Wrong specs, wrong tone |
Create platform-specific versions |
| Logo in first 3s |
Feels like a commercial, gets skipped |
Save branding for the end |
| Text in unsafe zones |
Cut off by platform UI |
Check safe zone per platform |
Checklist
Related Skills
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: belt app list
1---2name: video-ad-specs3description: Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad4---5
6> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
7
8# Video Ad Specs
9
10Create platform-specific video ads via [inference.sh](https://inference.sh) CLI.
11
12## Quick Start
13
14> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
15
16```bash
17belt login
18
19# Generate a vertical video ad scene
20belt app run bytedance/seedance-2-0 --input '{
21 "prompt": "vertical video, person excitedly unboxing a product, clean modern room, bright natural lighting, social media ad style, authentic feeling",
22 "ratio": "9:16",
23 "generate_audio": true
24}'
25```
26
27
28## Platform Specifications
29
30### TikTok
31
32| Spec | Value |
33|------|-------|
34| Aspect ratio | **9:16** (vertical) |
35| Resolution | 1080 x 1920 px |
36| Duration | 5-60 seconds (15-30s recommended) |
37| File size | Max 500 MB |
38| Format | MP4, MOV |
39| Sound | On by default (design with sound) |
40| Text safe zone | 150px from all edges |
41| Hook window | **1 second** — first frame must grab attention |
42
43### Instagram Reels
44
45| Spec | Value |
46|------|-------|
47| Aspect ratio | **9:16** (vertical) |
48| Resolution | 1080 x 1920 px |
49| Duration | Up to 90 seconds (15-30s for ads) |
50| Cover image | Separate upload, shows in grid |
51| Sound | On by default |
52| Caption area | Bottom 20% reserved for text overlay |
53
54### Instagram Stories
55
56| Spec | Value |
57|------|-------|
58| Aspect ratio | **9:16** |
59| Resolution | 1080 x 1920 px |
60| Duration | Up to 15 seconds per segment |
61| Swipe-up/Link | Available for ads |
62| Top/bottom | 14% top and 20% bottom = unsafe for key content |
63
64### YouTube
65
66| Format | Aspect | Duration | Skip |
67|--------|--------|----------|------|
68| Bumper | 16:9 | **6 seconds** exactly | Non-skippable |
69| Non-skippable | 16:9 | **15 seconds** | Non-skippable |
70| Skippable (TrueView) | 16:9 | Any length | Skip after **5 seconds** |
71| Shorts | 9:16 | Up to 60 seconds | N/A |
72
73Resolution: 1920 x 1080 (16:9) or 1080 x 1920 (Shorts)
74
75### Facebook Feed
76
77| Spec | Value |
78|------|-------|
79| Aspect ratio | **1:1** (square) or **4:5** (recommended for mobile) |
80| Resolution | 1080 x 1080 or 1080 x 1350 |
81| Duration | Up to 240 min (15-30s recommended) |
82| Autoplay | **Silent** — captions are essential |
83| Sound | 85% of Facebook video is watched **without sound** |
84
85### LinkedIn
86
87| Spec | Value |
88|------|-------|
89| Aspect ratio | **1:1** or **16:9** |
90| Resolution | 1080 x 1080 or 1920 x 1080 |
91| Duration | 3 seconds to 10 minutes (15-30s for ads) |
92| Tone | Professional |
93| Autoplay | Silent in feed |
94
95## AIDA Framework for Video Ads
96
97| Phase | Time | Goal | Technique |
98|-------|------|------|-----------|
99| **Attention** | 0-3s | Stop the scroll | Pattern interrupt, bold visual, question |
100| **Interest** | 3-10s | Keep watching | State the problem, show relevance |
101| **Desire** | 10-20s | Want the solution | Show the product/outcome, social proof |
102| **Action** | Final 3-5s | Click/buy/sign up | Clear CTA, urgency, offer |
103
104### Hook Techniques (First 3 Seconds)
105
106| Technique | Example |
107|-----------|---------|
108| Bold statement | "This tool replaced my entire marketing team" |
109| Question | "Why are you still doing this manually?" |
110| Surprising visual | Unexpected transformation, before/after reveal |
111| Pattern interrupt | Start mid-action, unusual angle, bright color |
112| Social proof | "2 million people switched to this" |
113| Pain point | "If you hate [common frustration], watch this" |
114
115## Creating Video Ads
116
117### Vertical (TikTok, Reels, Stories, Shorts)
118
119```bash
120# Hook scene (0-3s)
121belt app run google/veo-3-1-fast --input '{
122 "prompt": "vertical 9:16 video, close-up of hands struggling with tangled cables and messy desk, frustrated energy, shaky handheld camera, authentic social media style, bright lighting"
123}'
124
125# Solution reveal (3-15s)
126belt app run bytedance/seedance-2-0 --input '{
127 "prompt": "vertical video, smooth product reveal, clean wireless charging station on minimalist desk, satisfying organization transformation, bright modern room, social media ad aesthetic",
128 "ratio": "9:16",
129 "generate_audio": true
130}'
131
132# Add voiceover
133belt app run falai/dia-tts --input '{
134 "prompt": "[S1] Stop wasting time with this mess. This one product changed my entire setup. Everything charges. Everything is organized. Link in bio."
135}'
136
137# Merge video + audio
138belt app run infsh/video-audio-merger --input '{
139 "video": "solution-reveal.mp4",
140 "audio": "voiceover.mp3"
141}'
142
143# Add captions (critical for silent autoplay)
144belt app run infsh/caption-videos --input '{
145 "video": "ad-with-audio.mp4",
146 "caption_file": "captions.srt"
147}'
148```
149
150### Square (Facebook, LinkedIn Feed)
151
152```bash
153belt app run google/veo-3-1-fast --input '{
154 "prompt": "square 1:1 video, professional person at desk discovering a new software tool, laptop screen showing clean dashboard, natural office lighting, corporate commercial style, satisfied expression"
155}'
156```
157
158### YouTube Bumper (6 Seconds)
159
160```bash
161# 6-second bumper: one message, one visual, one CTA
162belt app run google/veo-3-1-fast --input '{
163 "prompt": "6 second product ad, quick montage of a sleek app being used on phone, fast cuts, modern, energetic, brand logo reveal at end, punchy and dynamic, wide 16:9"
164}'
165
166# Keep it tight
167belt app run falai/dia-tts --input '{
168 "prompt": "[S1] Your reports. Automated. Try DataFlow free."
169}'
170```
171
172## Captions Are Mandatory
173
17485% of Facebook and 40%+ of Instagram video is watched on mute.
175
176### Caption Best Practices
177
178| Rule | Reason |
179|------|--------|
180| Always add captions | Silent viewing is the default on most platforms |
181| Large, readable font | Small text is invisible on mobile |
182| High contrast | White text with dark outline/background |
183| Centered or bottom-third | Standard viewing position |
184| Max 2 lines at a time | More text = can't be read fast enough |
185| Key words in bold/color | Draws eye to important words |
186
187```bash
188# Generate captions from audio
189# (create SRT file from your script, then burn in)
190belt app run infsh/caption-videos --input '{
191 "video": "ad-video.mp4",
192 "caption_file": "ad-captions.srt"
193}'
194```
195
196## Ad Structure Templates
197
198### Testimonial Ad (15-30s)
199
200| Time | Content |
201|------|---------|
202| 0-3s | Customer states the problem they had |
203| 3-15s | How they discovered and tried the product |
204| 15-25s | The specific result they achieved |
205| 25-30s | Product name + CTA |
206
207### Demo Ad (15-30s)
208
209| Time | Content |
210|------|---------|
211| 0-3s | The problem (text or visual) |
212| 3-20s | Product demo showing the solution |
213| 20-25s | Key result/benefit |
214| 25-30s | CTA + offer |
215
216### Before/After Ad (15s)
217
218| Time | Content |
219|------|---------|
220| 0-3s | "Before" state (messy, slow, frustrating) |
221| 3-5s | Transition / product introduction |
222| 5-12s | "After" state (clean, fast, satisfying) |
223| 12-15s | CTA |
224
225## Common Mistakes
226
227| Mistake | Problem | Fix |
228|---------|---------|-----|
229| No hook in first 1-3s | Viewer scrolls past | Open with pattern interrupt |
230| Landscape video on TikTok/Reels | Letterboxed, looks amateur | Use 9:16 for vertical platforms |
231| No captions | Most viewers watch silent | Always add captions |
232| CTA too late | Viewers already left | Clear CTA within last 5 seconds |
233| Too long for platform | Forced skip or dropout | Match platform duration norms |
234| Same ad for all platforms | Wrong specs, wrong tone | Create platform-specific versions |
235| Logo in first 3s | Feels like a commercial, gets skipped | Save branding for the end |
236| Text in unsafe zones | Cut off by platform UI | Check safe zone per platform |
237
238## Checklist
239
240- [ ] Correct aspect ratio for target platform
241- [ ] Hook in first 1-3 seconds
242- [ ] Captions added (readable, high contrast)
243- [ ] CTA clear and within final 5 seconds
244- [ ] Duration matches platform norms
245- [ ] Text outside platform unsafe zones
246- [ ] Audio designed for both sound-on and sound-off
247- [ ] Platform-specific version (not one-size-fits-all)
248
249## Related Skills
250
251```bash
252npx skills add inference-sh/skills@ai-video-generation
253npx skills add inference-sh/skills@video-prompting-guide
254npx skills add inference-sh/skills@text-to-speech
255npx skills add inference-sh/skills@prompt-engineering
256```
257
258Browse all apps: `belt app list`
259
101-skills