The demo reel / NAKHLA breakdown
An Arabic dates ad where guests do the talking
This page is a full production breakdown of a short vertical ad for NAKHLA, a fictional dates gift box we invented for our own portfolio. No client, no brief, no order. Dates are a hospitality product in the Gulf: their value is the moment of serving, not the taste description. So the ad stages that moment.
The finished ad. 12 seconds, 9:16, sound on. Spoken in Modern Standard Arabic; the words are written out below in Arabic and in English. Every frame AI-generated. The “portfolio demo” watermark is ours — client deliveries ship clean.
The brief we wrote ourselves
- Product
- A fictional gift box of almond-stuffed, chocolate-coated dates we invented.
- Audience
- Gulf households and businesses buying premium hospitality gifts in date season.
- Constraint
- No filmed footage, a single continuous shot, runtime locked to the voiceover.
- Format
- Majlis presentation · talking head · spoken Arabic
- Niche
- Food & Beverage
The opening line, as it is spoken
نخلة — تمر فاخر محشو باللوز ومغلف بالشوكولاتة.
In English: “NAKHLA — fine dates stuffed with almonds and coated in chocolate.”
The whole spoken line
نخلة — تمر فاخر محشو باللوز ومغلف بالشوكولاتة. قدمتها لضيوفي فسألوني: من أين هذه؟
NAKHLA — fine dates stuffed with almonds and coated in chocolate. I served them to my guests and they asked me: where are these from?
The English here is a translation for this page. It is not spoken in the ad, and it is not burned into the video.
The line names the box first and then hands the ending to somebody else: the guests ask where the dates are from, and their question does the work a claim would have done badly. Praise from the seller is a claim. A question from a guest is evidence.
Why this format. Dates are a hospitality product, sold in the room where guests are received. A presenter in a majlis opening the box toward camera restages the act of serving. The setting carries the premium feel, so the product never has to shout.
How it was built
- 01
Script first
The spoken line is written in Modern Standard Arabic before any image exists, and it is measured by ear rather than by word count. A script that looks short on the page can run long once it is read aloud, so it gets cut back until it sits inside the time available.
- 02
Voice before picture
The Arabic voiceover is generated with a text-to-speech model and approved as a standalone file before a single frame is drawn. This is the inversion from our English ads, where the video model generates the audio inside the same pass that generates the picture.
- 03
Hero still
One vertical image, generated with Nano Banana Pro. Framed like a phone photo rather than a studio product shot: the presenter and the product in hand, the brand name legible, and light with a plausible source in the room.
- 04
Motion and lip-sync
The still goes to Seedance 2.0 as frame one, with the approved audio file alongside it as a reference, so the mouth moves to the actual Arabic speech instead of a dub laid over it afterwards. The audio leads the picture here rather than the other way round, which is what the lip movement is following.
- 05
Check before keep
Nothing survives because it looked fine as a thumbnail. We read the stream data with ffprobe, build a contact sheet of frames with ffmpeg, and compare the spoken audio against the written script. Takes that drift from the brief get regenerated, not patched.
- 06
Finish
The approved take is cut and packaged with ffmpeg for wherever it will run. Vertical for Reels and TikTok here; the same take can be reframed for feed or landscape if the brief asks.
What to watch for
Mouth and voice
You need no Arabic to check this: his lips move with the spoken words, because the voice track led and the video followed.
Majlis details
The dallah, lantern, and carpet behind him do the category work, placing the box in a room of hospitality without any copy.
The open box
He raises the open box in a careful grip and holds it up to the camera, letting the lamp light catch the coated dates.
Two things about Arabic we will not smooth over
The logo on the product is in Latin letters, not Arabic ones. The reason is technical and known: image models do not render connected Arabic script reliably, and it comes out malformed. We chose a clean Latin wordmark over broken Arabic type. If your brand's Arabic logotype has to appear on the product in frame, say so at the brief stage, because it changes how the shot is built.
The voice is Modern Standard Arabic, and it is generated, not a hired voice actor. That is the right register for a pan-Gulf audience and the wrong one if you specifically need spoken Khaleeji dialect or one particular human voice. It is the single thing on this page you cannot judge for yourself if you do not speak Arabic, so we would rather write it down than let the video imply otherwise.
The take we threw away
The first version of this script was longer. It opened with a line meaning "these are not ordinary dates" and closed with an explicit invitation to try them. When the voiceover was generated, the Arabic reader's pace came out slower than the written length suggested and the take ran past the time available, so it was scrapped and the script rewritten shorter. The cost was real: the opening line and the closing invitation were both lost, and the guests' question was left to carry the ending alone. In Arabic, script length is measured by ear, not by counting words on the page.
What this page is not
Every frame is AI-generated and NAKHLA is a brand we invented. The ad never ran as paid media, so we claim no performance numbers. With a real box to ship, we would build the ad around real footage of it, and photograph the Arabic on the lid instead of working around it.
We have no published reviews yet, so we are not going to borrow credibility we haven't earned. No client names, no engagement numbers, no invented case studies. What we can show you is the work and the method, in full, and let you judge whether it clears your bar.