Prepare the handheld photo
Create one with handheld product photos or upload your own. Pick a frame where the product shape, colours and label are right and the person has agreed to appear.
Product explainer videoComing soon
A person, your product in hand, saying your line.
Start from a handheld product photo you have approved, write a short line about the product, choose the language and voice, and get a talking clip for listings and short video.
Open the workspaceThis tool is in private testing and is not open to all accounts yet. The page describes how it will work; the workspace shows which tools your account can use today.
How it works
The TrendRemix product explainer video turns one confirmed handheld product photo into a short clip of the person talking about the product. The photo is the first frame; the person keeps the product in hand with the label toward the camera and says your script, 3 to 400 characters, in one of 13 languages. You can keep the voice generated with the video, or pick a studio voice, in which case your script is read in that voice, fitted to the clip and lip-synced afterwards. Clips are 5 or 10 seconds in 9:16, 3:4, 1:1 or 16:9 and are saved as MP4 files.
From input to finished result.
Write the line and choose the voice
Keep it to one or two short sentences; roughly 25 English words or 45 Chinese characters fit a 10 second clip. Check the quote, which includes the lip-sync step when you pick a voice.
Review sound and picture
Watch with sound on. Check the mouth against the words, the hand around the product and the label, then download the clip or keep it in your assets.
What you can do
Opens on your handheld shot
The approved photo is the first frame, so the person, product and setting you picked carry into the clip.
Two voice routes
Use the voice generated with the video for natural room sound, or a studio voice for a consistent brand voice, lip-synced after the clip is made.
13 spoken languages
Write the line in the target language and the person speaks it, so one photo can serve several storefronts.
Script length checked up front
The form estimates speaking time and rejects a line that cannot be said within the clip, before anything is charged.
Who it is for
- Listing clips
- A short talking demo that states one selling point while the product stays in view.
- Openers for short video
- A 5 second line to camera at the start of an ad or post.
- Storefronts in other languages
- Reuse the same photo with the line rewritten in Spanish, Thai or Arabic for a new market.
At a glance
| Input | One handheld image, JPG, PNG or WebP, up to 20 MB |
|---|---|
| Script | 3–400 characters, must fit the clip length |
| Languages | 13 spoken languages |
| Voice | Generated with the video, or a studio voice with lip-sync |
| Length and format | 5 or 10 s; 9:16, 3:4, 1:1 or 16:9 |
| Output | MP4, saved to your asset library |
| Cost | Credits by length, plus lip-sync for a chosen voice; shown before you submit |
Before you download
- Check lip sync word by word, especially when a chosen voice was applied after generation.
- Watch the fingers around the product; extra fingers or a hand passing through the product are common errors.
- Compare the product's size in the hand with the photo and look for changes in shape.
- Read the label in several frames, because printed text can blur or change as the product moves.
- Listen for mispronounced product names and respell them in the script if needed.
Questions and answers
Where does the handheld photo come from?
Use the handheld product photos tool to place your product in a model's hand, or upload a photo you shot. Anyone shown must have agreed to appear.
What is the difference between the two voice options?
Generated with the video means the speech is created together with the picture. A chosen voice reads your line in a studio voice, is fitted to the clip length and has the mouth re-synced to it, which adds a step and cost.
My script was rejected as too long. Why?
Speaking time is estimated at about 2.5 words a second, or 4.5 characters a second in Chinese, Japanese and Korean, and may exceed the clip by about a second at most. Shorten the line or switch to 10 seconds.
Can it show the product being used?
The motion is a person holding the product toward the camera and talking, with small hand movements. For other actions, use the AI video generator with the photo as the start frame.
Is this the same as an AI presenter video?
No. A presenter video is a talking presenter in front of a background. A product explainer starts from a photo of a person holding your product and keeps it in their hand.
Bring your product. Leave with something new.
Every result lands in your asset library, ready for the next tool.