AI Ad Maker: How to Turn One Product Photo into a Video Ad in Arabic
Make a video ad from one product photo with Vocla's AI ad maker: it reads your product, writes the script in your customer's Arabic dialect and voices it.
In this article
Open the Ad maker in Vocla and upload one to four product photos. The AI reads the product and suggests ad angles; you pick a style such as Luxury reveal or Flash sale and add your price and offer. It writes the script in your customer's dialect, voices it, builds every scene from your photos, and lets you approve the scenes before rendering a ready MP4.
01What Vocla's Ad maker does
The Ad maker turns your product photos into a short video ad that's ready to post. You bring the photos and the offer; it handles the rest. It works out what the product is, writes the ad in your customer's dialect, voices it with a professional Arabic voice, builds every scene from your real photo, then adds Arabic captions and music. No photographer, no voice actor, no editing software.
It's built for online stores, Instagram and TikTok sellers, and marketers who need a fresh ad every week for a different product. Most stores already have decent product photos. What they don't have is the time or budget to shoot a video for every item, and that's the gap this tool fills.
| You give it | It does |
|---|---|
| One to four product photos | Reads the product: name, category, key features, who buys it, plus three ad angles |
| An ad style and an occasion | Sets the scene pacing, camera moves, music and caption look |
| Price, discount and store name | Writes a script in your dialect: hook, benefit, offer and a clear call to action |
| A voice and a format | Voices the script and builds the scenes from your photos in the frame you chose |
| Your approval of the scenes | Renders the ad and mixes voice, captions and music into an MP4 |
This differs from plain text to video in one important way: the product is the starting point. When scenes are generated from a written description, you get something that looks like your product but isn't it. In the Ad maker, every scene starts from your own photo, and your hero shot opens the ad.
02Prep your product photos first
The photo is the first frame of the ad and the reference for every scene after it, so five minutes of prep shows in every second. You don't need a studio; a sharp phone photo is enough.
- Soft light: daylight from a window beside the product beats a flash.
- A simple background: white, marble, wood or one flat colour, so the AI can separate the product.
- A few angles: a front shot, a close-up of the detail that sells it, and the product in use.
- Centred, with room around it: camera moves need margin.
- Match the frame: a portrait photo for a 9:16 ad, a square or landscape one for 1:1 or 16:9.
Don't put the price, discount, stickers or a watermark on the photo itself. Text inside the image warps once it moves. The offer belongs in the script and the captions, and the Ad maker adds both for you.
Make your strongest photo the hero shot. It opens the ad, and the first two seconds decide whether someone stops scrolling. The other photos open the following scenes in order.
03Step by step: from photo to finished ad
These are the steps as they appear in the Ad maker on the web and in the mobile app. Your first ad takes about three minutes before rendering; later ones go faster.
- 1Product photos: upload one to four photos, or take one with your phone camera, and choose the hero shot.
- 2Understand my product: the AI reads your photos and fills in the product name, category, key features and who buys it, with three suggested ad angles. Check it and edit anything.
- 3Ad style: pick one of five styles, plus an occasion if you have one, such as Ramadan, Eid or White Friday.
- 4Script and offer: choose the ad length and add the price, discount, store name and call to action. It writes the script in your dialect; ask for another version or edit any line yourself.
- 5Voice and format: choose the voice, frame, quality, caption style and music. The credit cost is shown before you commit.
- 6Review the scenes, then render: it records the voice and plans the scenes from your photos. Check each scene and its prompt, regenerate any you dislike, then approve and render.
When rendering finishes you download an MP4 with the voice, captions and music mixed in. The ad is also saved under Your ads, so you can come back to it or make a variation.
Don't skip the Understand my product check. If the AI lists a feature you don't offer, or the wrong audience, fix it before the script is written, because the script and the scenes are built on it.
04Which ad style fits your product?
The style shapes the whole ad: the number and pace of scenes, the camera moves, the mood, the music and the caption look. You can try several styles on the same product and compare.
| Style | Feel | Works for |
|---|---|---|
| Luxury reveal | Slow and calm, gold light, rich close-ups | Perfume and oud, abayas, jewellery, watches, premium gifts |
| Flash sale | Fast and bold, price and offer up front | White Friday, end-of-season clearances, Ramadan and Eid deals |
| Unboxing and everyday use | Natural shots of the product being opened and used at home | Cosmetics, small gadgets, home goods |
| Feature highlights | Clean studio shots, one feature per scene | Electronics, appliances, skincare with active ingredients |
| Gift idea | Warm and festive, the product revealed as a present | Eid, Ramadan, Mother's Day, graduations, weddings |
For seasonal campaigns, add the occasion on top of the style: Ramadan, Eid or White Friday. The occasion brings its look to the scenes and the script, while the style still sets the pace. A perfume for Eid works well as Gift idea with the Eid look; a discounted phone for White Friday as Flash sale with the White Friday look.
05The script: your offer in your customer's dialect
The Ad maker writes the script from what it learned about the product and the offer you entered, so the clearer your details, the stronger the copy. Four fields matter most: price, discount, store name and the call to action, such as Order via the link in bio or Order on WhatsApp.
Here is a 15-second Saudi script it might write for a black abaya with gold embroidery, in the Luxury reveal style:
عباية تمشي معك من الصبح لين الليل.
قماش ينساب، وتطريز ذهبي يلمع بهدوء.
وهذا الأسبوع عليها خصم خمسطعش بالمية.
اطلبيها اليوم من الرابط في البايو.An abaya that moves with you from morning till night. Flowing fabric, gold embroidery that gleams softly. And this week it is 15% off. Order yours today via the link in bio.
And the same idea for an Egyptian store selling wireless earbuds, in the Flash sale style:
السماعات اللي الكل بيسأل عليها بقت بنص التمن!
بطارية تكفيك اليوم كله، وصوت نضيف في الزحمة.
العرض لحد آخر الأسبوع بس.
اطلبها دلوقتي قبل ما تخلص.The earbuds everyone asks about are now half price! A battery that lasts all day and clean sound in a crowd. The offer ends this weekend. Order now before they sell out.
A practical length rule: a 15-second ad holds roughly 30 to 40 words. The Ad maker shows the script's estimated duration against your target length and tells you when it runs long.
Write prices and percentages the way they're spoken in the dialect so the voice reads them naturally. And don't claim what you can't prove, such as best-selling: you're responsible for every word in the ad.
06Voice, frame, captions and music
The voice is what makes an ad feel local. In the Ad maker you choose a professional Arabic voice in your customer's dialect: Saudi, Emirati, Kuwaiti, Egyptian, Levantine, Maghrebi or Modern Standard Arabic, and you can play each voice before choosing.
| Frame | Where it runs | Tip |
|---|---|---|
| 9:16 vertical | TikTok, Reels, Snapchat, Stories, Shorts | Keep the product and price mid-frame; app buttons cover the edges |
| 1:1 square | Instagram and Facebook feed, WhatsApp Status | The safest single format when one video runs in many places |
| 16:9 landscape | YouTube, your store's product page, banners | Room for a longer feature walk-through |
Arabic captions are added as their own track on top of the video, never drawn inside the AI footage, which is why the letters always come out correct and right to left. There are three caption styles: clean, bold, and karaoke, where each word lights up as it is spoken. Most people watch ads muted, so keep captions on.
Music is optional and ducks automatically under the voice so the offer stays clear. Each style suggests a fitting track, and you can change it.
07Plans, cost and limits
The Ad maker is included from the Starter plan at $4.99 and up. Free doesn't include video, but it lets you hear your ad script in our voices before you subscribe.
| Plan | Video seconds a month | Longest ad | Quality |
|---|---|---|---|
| Starter, $4.99 | 30 seconds | 15 seconds | 720p, 9:16, watermark |
| Creator, $13.99 | 60 seconds | 20 seconds | 720p, every format, no watermark |
| Professional, $29 | 300 seconds | 60 seconds | 1080p, no watermark |
| Business, $99 | 900 seconds | 120 seconds | 1080p, adds Vox Video Pro |
In practice, Starter covers one 15-second ad or two 10-second ads a month, the cheapest way to test video ads. Creator removes the watermark, adds square and landscape, and covers about four 15-second ads. If you advertise several products every week, Professional fits better: 300 seconds means up to twenty 15-second ads, in 1080p. The credit cost depends on the quality tier and the number of scenes; the Ad maker shows the exact figure before rendering, and a scene that fails to render is refunded.
- The video starts from your photo and stays close to it, but it isn't a pixel-perfect copy in every frame: small labels and logos can drift as the camera moves, so check each scene before publishing.
- Vocla gives you an MP4 to download; it doesn't post to your store or social accounts.
- Use product photos you own, and avoid people who haven't given permission or other brands' logos.
Key takeaways
- The Ad maker turns one to four product photos into a video ad with an Arabic voice, captions and music.
- Check what the AI understood about your product before the script is written; everything is built on it.
- Pick the style by product and occasion, and write prices and offers the way your customer says them.
- Included from Starter at $4.99; Professional suits stores that advertise every week.
Frequently asked questions
How many photos do I need to make an ad?
One photo is enough, and you can upload up to four. The hero shot opens the ad, and each extra photo opens one of the following scenes.
Is the Ad maker included in Starter?
Yes. The Ad maker is included from Starter at $4.99: vertical 9:16 ads up to 15 seconds, 30 seconds of video a month, with a watermark. For no watermark and every format, choose Creator or higher.
Will my product look exactly like the photo?
Every scene starts from your photo and stays close to it, but small text and logos can change as the camera moves. Use clean photos, review each scene, and regenerate any you dislike before rendering.
Which dialects can the script and voice use?
The one you choose: Saudi, Emirati, Kuwaiti, Egyptian, Levantine, Maghrebi or Modern Standard Arabic, plus English, French and other languages. The voice is a Vocla voice, so the dialect sounds right.
Can I run the ad as a paid ad and use it in my store?
Yes. Paid plans that include the Ad maker include commercial use, so you can run it as a paid ad or add it to a product page. Make sure your claims are accurate and follow each platform's ad policies.
- #AI ad maker
- #Ecommerce ads
- #Product photo to video
- #TikTok and Snapchat ads
Read next
- AI videoOctober 3, 2026 · 7 min read
AI Video Ads in Arabic: From Script to Instagram and TikTok
Read article - AI videoOctober 3, 2026 · 6 min read
Why AI Video Garbles Arabic Text, and the Reliable Fix
Read article - AI videoOctober 3, 2026 · 7 min read
Arabic Text to Video with AI: How to Turn a Script into a Finished MP4 with Voice and Captions
Read article