varg-dropship-reel
Makes the 60-second faceless dropshipping "guide" reel end to end: a viral-looking product hook, a laptop on a zigzag tablecloth with a hand pointing a marker at the product cost, the store price and the demand chart, then each step (research tool → store → AI ad tool → Instagram → supplier ships), and a night-skyline ending shot on an iPhone with "Comment GUIDE". Script template, AI shots on varg (Seedance 2.5, GPT Image 2.5, Wan 3, ElevenLabs), word-by-word lime captions, the comment-to-DM funnel. Use when an e-commerce seller, dropshipper, affiliate of a product-research or AI-ad tool, or course creator asks for a product reel like @tradelle's, "a reel showing a product, its price in China and on Shopify", a "comment GUIDE" reel, a laptop-and-pen screen walkthrough, or one such reel per product every day. Not for the hook alone (use varg-product-hook), talking-head UGC ads, or screen recordings of software with a cursor (find those with video-skills).
Dropshipping guide reel
One template, a new product every day. Built from four @tradelle reels (Sept-Oct 2026, 56-64 s, 1080×1920) that share the same skeleton and almost the same voiceover; only the product, the prices and the hook change.
| Beat | Time | Picture | How we make it |
|---|---|---|---|
| Hook | 0-13 s | The product in action: real-looking phone or security-cam footage | varg-product-hook (Seedance 2.5 from product photos) |
| Price math | 13-27 s | Laptop, hand with a marker points at cost, sell price, demand chart | Screenshots → GPT Image 2.5 frame → Seedance 2.5 (or film it) |
| Steps | 27-53 s | The same desk, the pen walks through each tool's screen | Same, one shot per screen |
| CTA | 53-60 s | Night skyline through an apartment window, iPhone look | Wan 3 or Seedance 2.5 once, reuse forever |
Captions: 1-2 words at a time, bold uppercase, white with a black outline, prices and keywords in lime, at 60 % of the height. Voice: one flat, confident male narrator, about 2.6 words per second, no music or a very quiet bed.
Generation runs on varg: the varg-ai skill (REST at https://api.varg.ai/v2) or the varg MCP server (https://mcp.varg.ai/mcp: call_tool, get_job, estimate_cost, create_upload). Every call returns a job; poll GET /v2/jobs/{id} until completed, the file is at output.outputs[0].url. Image-to-video jobs took 5-10 minutes in our test; one text-to-video job waited about an hour in the queue. Start them all at once and do the next step while they run.
1. Ask once, then go
Collect: the product (store or supplier link, 1-3 photos), cost price and sell price, which tools the steps name (the research tool, store builder, AI ad tool, supplier: the ones you're an affiliate of, or your own store), the CTA keyword (default GUIDE), and the language.
Then offer these choices in one message, each with a default:
- Hook: AI remake from product photos (default) / your own footage. Archetype: backyard camera, torture test, problem → solution, satisfying close-up, gift reaction.
- Laptop shots: full AI from screenshots (default) / film them yourself (free, looks 100 % real, guide in
references/screen-demo.md). - Ending: AI night skyline (default, make once and reuse) / your own phone clip / stock.
- Voice: ElevenLabs
eleven_v4, voice "Brian" (default) / another voice / your own recording.
Quote the price before generating (POST /v2/estimate or MCP estimate_cost per clip). What our test paid (Oct 2026): 6 s seedance_2_5 hook 231 credits, 5 s laptop shot 193 + its frame 23, voice 3, word timings 3. A full AI reel with 3 hook clips, 8 laptop shots and the skyline comes to about 2,500-2,700 credits; with real laptop footage, about 1,000. Reusing the skyline and filming the laptop brings the next reels down to about 700 credits each (hook + voice).
2. Write the script
Fill the template in references/script.md (140-160 words for 55-60 s). Put the exact prices you'll show on screen into the script. No income promises (see the claims section there).
3. Make the pieces (start all video jobs in parallel)
Hook (0-13 s): follow varg-product-hook: 2-3 clips of 4-6 s on seedance_2_5, 9:16, 720p, the product photo as @image1.
Laptop shots (13-53 s): references/screen-demo.md. In short:
- Screenshot every screen the script names (research page with the cost, store page with the price, demand chart, each tool's home page, the AI ad tool, Instagram, the order page, a flow graphic).
- First frame:
gpt_image_2_5puts the first screenshot on a MacBook on a zigzag tablecloth with a hand holding a marker. - Every later screen: edit that first frame and change only the screen, so the desk, light and hand stay identical.
- Animate each frame on
seedance_2_5for 5 s with a locked camera, a static screen and a pen path through the items in script order.
Skyline ending (53-60 s): references/cta-and-funnel.md has the iPhone-look prompt. Text-to-video on wan_3 (60 credits for 6 s) did it well in our test. Make 2 variants once and reuse the better one in every reel.
Voiceover:
curl -s -X POST https://api.varg.ai/v2/speech -H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "eleven_v4", "voice": "Brian", "text": "<the script>"}'
Word timings for the captions: transcribe the voiceover with groq_whisper_large_v3_turbo. It returns data.words with a start and end per word; whisper_large_v3 returns only sentence chunks.
curl -s -X POST https://api.varg.ai/v2/tools/transcription/call -H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "groq_whisper_large_v3_turbo", "audio_url": "VOICEOVER_URL", "language": "en"}'
# poll the job, then save its result (the object with "words") as words.json
4. Cut it
Download every clip into one folder, then:
mkdir -p fonts && curl -sL -o fonts/Bangers-Regular.ttf \
https://github.com/google/fonts/raw/main/ofl/bangers/Bangers-Regular.ttf # free, close to the originals' comic bold
node scripts/captions.mjs words.json captions.ass --keywords "shopify,profit,demand,free,guide,china"
node scripts/assemble.mjs edit.json
edit.json is the edit list: one entry per cut, timed to the voiceover (use the word timings in words.json to place each cut on the word that names the next item):
{
"out": "reel.mp4", "voiceover": "vo.mp3", "captions": "captions.ass", "fontsdir": "fonts",
"shots": [
{ "file": "hook1.mp4", "in": 0, "dur": 3.0 },
{ "file": "hook2.mp4", "in": 0.5, "dur": 2.6 },
{ "file": "research.mp4","in": 0, "dur": 3.0 },
{ "file": "store.mp4", "in": 0, "dur": 4.1 },
{ "file": "research.mp4","in": 2.6, "dur": 2.4, "zoom": 1.08 },
{ "file": "skyline.mp4", "in": 0, "dur": 4.6 }
]
}
zoom punches in (use it when you reuse a clip), speed below 1 slows a shot, and a shot longer than its source holds the last frame. Shots should add up to the voiceover length. The script picks up Homebrew's ffmpeg-full by itself when the default ffmpeg can't burn subtitles.
ffmpeg without captions support. Homebrew's ffmpeg has no libass since 2025 (ffmpeg -filters | grep subtitles prints nothing). Install the keg-only ffmpeg-full next to it (brew install ffmpeg-full); it doesn't replace ffmpeg. Seen on macOS 15.1 (2026-10-27): the install upgraded shared libraries, after which the old ffmpeg failed to start (Library not loaded: libx265…) and ffmpeg-full failed on freetype (Library not loaded: /usr/lib/libhvf.dylib). Fix: brew upgrade ffmpeg and brew reinstall --build-from-source freetype. Don't run this on someone's machine without asking: it changes their system Homebrew.
Check the result: watch it once with sound and once muted; every price on screen must match the voice and the caption at that moment.
5. Post and catch the comments
Caption Best time to start is here 🤝 #entrepreneur #onlinebusiness #ecommerce (the originals' exact line), a ManyChat comment trigger on the keyword that DMs the guide, and the AI label where the platform asks for it. Setup and what to put in the guide: references/cta-and-funnel.md.
Tested
2026-10-27, LED pet nail clipper, everything on varg: product packshot and two screens on gpt_image_2_5; hook and two laptop shots on seedance_2_5, the skyline on seedance_2_5 and wan_3 (9:16, 720p); voice on eleven_v4 "Brian"; words on groq_whisper_large_v3_turbo; then captions.mjs + assemble.mjs. The hook read as phone footage with the product intact. In the laptop shots every price stayed correct for the full 5 s; only small grey body text went soft. The second screen, made as an edit of the first frame, matched the desk and hand exactly. The 23 s test cut (hook → research page → store page → skyline, Bangers captions): https://s3.varg.ai/files/194b94d0-58ff-4e8b-91de-4f1959d04013/file_2faa92a85cb7.mp4
Rules
- Real prices, real store, real screenshots. No fake reviews, sales counts or income claims.
- Don't repost other people's videos as the hook. Remake the idea with your product (
varg-product-hook). - Say it's an ad when you're paid or an affiliate; label AI footage where the platform asks.
- Keep Burj Khalifa out of focus in paid ads (Emaar wants approval for ad use).
- Re-running a byte-identical request is a free cache hit; change a word to get a new take.
Files
reel/
script.md # filled template
product.png # packshot (and any extra product photos)
screens/*.png # screenshots, one per screen named in the script
frames/*.png # laptop first frames (gpt_image_2_5)
clips/*.mp4 # hook, laptop shots, skyline
vo.mp3 words.json captions.ass fonts/
edit.json reel.mp4
Related skills
varg-product-hook (the hook), varg-ai (models, uploads, prices, cloud render), media-download (save reference reels), short-form-ffmpeg-cookbook (more edits: zoom punches, speed ramps, loudness), video-skills (other ad formats).
- Downloads
- 68All time
- Security audit
- Review
- Last updated
- 3d ago
- Current version
- v1.0.0
- License
- MIT-0
