AI Product Video Generator

You already have the photography. What the listing needs is fourteen more seconds of it: the cap coming off, the light moving across the label, the sound of the thing actually working. Write that once and get it back with the audio already in it.
Your first one is free. No card.

Describe the shot

0 / 7000

This run spends credits — the free clip is 4s · 768P · 16:9.

Sign up free and your first MiniMax H3 clip renders 4s · 768P · 16:9, with sound. A plan raises the ceiling to 15s, 2K and four at a time — the free clip is a size, not a different model.

  • Upload the packshot rather than describing the product — a written description invents a different bottle every take
  • Name the material, not the mood: brushed aluminium, matte silicone, condensation on cold glass
  • Say what it sounds like. The click, the pour, the fabric — the audio is generated with the picture and cannot be added afterwards
  • Marketplaces want vertical; 9:16 bills at the same per-second rate as everything else

No card: every clip on this page plays without an account, and a free account runs one of your own — 4s, 768P, with sound, no watermark, yours to download and to use commercially.

Four product films and the complete prompt behind each. Every card opens the whole brief.

AI product video: fruity biscuits and the fruit they are made from orbit on colour backdrops, cutting hard to a beat

Four flavours, one spot

Prompt in, product out

The brief on the left. What it gave back on the right.

Four flavours, one spot16:9 · 15s · 1 reference image

The whole brief is arrangement and cadence. Four flavours, a geometric array, the fruit orbiting in, every cut landing on the beat — and all of it written out beat by beat, with one reference image holding the biscuit itself. Nothing here describes a feeling; every line describes a frame.

A bright, high-energy commercial for a fruit-filled sandwich biscuit, floating against seamless colour backdrops that change with the flavour. The biscuit is reference Image 1: hold its shape, crimped edge and dimple pattern in every shot. Studio macro light, no hands, no packaging, no on-screen text. Cut on the beat of an upbeat electronic pop track. 0-2s: coral-pink backdrop. One biscuit hangs dead centre and turns slowly on its own axis while whole and halved strawberries tumble and orbit around it, some drifting past the lens close enough to blur. 2-3s: cut on the beat to mint green. Four green apples float together into a tight cluster in the middle of frame, then split apart to reveal the biscuit hanging behind them. 3-5s: the apples clear and two dark grapes swing in either side of the biscuit; a full bunch of grapes then fills the frame and the backdrop turns lilac. 5-7s: the biscuit alone on lilac, a slow light sweep crossing the backdrop behind it, then three oranges bounce into frame around it. 7-8s: warm-orange backdrop. One orange bursts open in slow motion, pulp and juice spraying outward in macro. 8-9s: the frame settles back on the single biscuit, floating on peach. 9-11s: pull out to a large ordered grid of the biscuits laid flat on pink, evenly spaced and all facing the same way; the camera drifts across the grid. 11-14.5s: one continuous slow push in through the grid, the biscuits growing until the lens is inside the crumb — extreme macro across the dimpled surface. 14.5-15s: lift to a side-on hero of one biscuit, the strawberry filling glossy between the two halves, and hold. Audio: upbeat electronic pop with a four-on-the-floor kick, a crisp whoosh on every colour change, a wet burst on the orange, a dry crumb crunch as the macro lands. No voiceover.

AI product video: fruity biscuits and the fruit they are made from orbit on colour backdrops, cutting hard to a beat
A character sells the product16:9 · 15s · 1 reference image

A product film does not have to show a person using the product. This one is a story with a punchline, and the product is the payoff — the fruit is the hero, the lizard is the reason you are still watching at eight seconds. Fifteen seconds of it, timed beat by beat and printed whole below.

A 3D animated commercial in the register of a high-end animated short, with a streak of exaggerated humour. Bright translucent colour, soft desert light, delicate skin texture, dreamy macro depth of field. The desert horned lizard is reference Image 1: keep its markings, horns and expression identical in every shot. 0-2.5s: a desert scorched by the sun, the air shimmering with heat. Wide shot, horizon high, dunes running back to nothing. The lizard drags itself across the scalding sand, tongue slightly out, swaying every couple of steps as though it is about to evaporate. 2.5-6.5s: cut in close on its face, then closer still. Eyes glazed, breath shallow, grains of sand stuck to its snout. The camera stays down at sand level and moves with it. 6.5-7.5s: its nose twitches and it stops. A cool, plump, dew-covered grapefruit sits half-buried in the sand just ahead, catching the light with a hard sparkle. 7.5-9.5s: hold on the reaction — the eyes go wide, the grapefruit soft in the background behind its head. 9.5-11s: it scrambles forward and throws both front legs around the fruit. 11-14.5s: it lies against the grapefruit hugging it, cheek pressed to the rind, blissful. Push into macro on its hands gripping the peel and the beads of dew running down. 14.5-15s: it bites. The rind splits and the pulp bursts open in extreme slow-motion macro, juice thrown toward the lens. End there. Audio: dry desert wind and heat haze through the opening, a soft sparkle as the fruit is spotted, a rising musical swell under the scramble, a loud wet crack on the bite. No voiceover, no on-screen text.

AI product video: a 3D animated desert lizard bites a grapefruit and a wave of juice turns the desert into a sea
Setup, step by step16:9 · 15s · 4 reference images

The unglamorous one that sells the most. A setup walkthrough, four steps, each pinned to its own reference image so the machine in the last shot is the machine in the first. This is the video that stops the return — and every beat is timestamped, which is the reason the pacing comes back right.

A 15-second setup tutorial for a capsule coffee machine on a bright kitchen counter. Hands only, no faces. Every step is pinned to its own reference image: Image 1 the machine body and water tank, Image 2 the drip tray, Image 3 the used-capsule box, Image 4 the tank at its MAX line. Clean daylight, real hands at real speed, no on-screen text. 0-1.5s, step one, the water tank. Medium shot from slightly above, the back of the machine. Two hands lower the transparent tank onto the rear of the body and press it straight down until it seats. Voiceover: "Start with the water tank. Line it up with the slot at the back and push down until it clicks." 1.5-5s, step two, the drip tray. Close-up at counter height, front of the machine. One hand slides the black drip tray horizontally into the rails at the base, backs it out to show the fit, then pushes it in flush. Voiceover: "Next, the drip tray. Slide it into the rails at the bottom until it sits flush with the body." 5-8.5s, step three, the capsule box. Close-up from slightly low, the cavity above the tray. Two hands align the white used-capsule box with the recess and push it in level with the tray front. Voiceover: "Now the used-capsule box. Push it in until it is level with the tray. Spent capsules drop in here on their own." 8.5-15s, step four, the first fill. Cut to a tighter side view of the tank on the machine, the MAX line dead centre of frame. A hand lifts the lid and pours clear water from a glass jug in a steady stream; the level climbs, the camera holds while it stops just under the MAX line, and the lid closes. Voiceover: "Fill the tank with fresh water, stopping just under the MAX line, then close the lid. That is the setup done." Audio: quiet kitchen room tone, a firm click as the tank seats, a plastic slide on the tray, water running into the tank. One calm, unhurried voiceover line per step, no music.

AI product video: hands install the water tank on a capsule coffee machine, then run the first rinse, shot step by step
Borrow the cut, not the footage16:9 · 14s · 1 image + 1 reference clip

The shortest prompt on this page and the most useful trick on it: hand it an ad whose pacing you like, hand it your product, and say take the camera moves and the cut points from the clip, take the product from the image. You are not copying the footage. You are copying the edit.

Take the camera movement and the editing rhythm from reference Video 1, and take the product from reference Image 1: a pair of over-ear headphones. Build an advertising short around them in scenes that suit the product's tone — modern, spare, a little cold. Keep the switching points between product close-ups and wide scene shots where the reference clip puts them, and match its motion speed and transition style.

AI product video: a headphone advert cutting between city panoramas and product close-ups on the rhythm of a reference clip

What this is, and what it is not

A packshot is already most of the work. This is the other fourteen seconds.

This part goes first, because it decides whether you should be here at all. If what you need is your exact product, frame-true, on a white background for a marketplace that checks — shoot it, or hire the studio. A video model redraws every pixel, and your bottle is inside every frame it draws.
What it is good at is the part a photograph cannot do: the move, the light travelling across a surface, and the sound of the thing working.

The prices are why people search for this. A basic e-commerce product video is quoted at $500 to $5,000 and takes three to fourteen days; a studio packshot day costs more than that before anyone edits anything. The AI tools in between are subscriptions: $23 a month at the cheap end, $39 to $99 at Creatify, and the talking-actor tools run $110 a month for ten videos.
A fifteen-second product film here is 125 credits, about $2.75, and it arrives with its own audio. That is not a claim that it replaces your photographer. It replaces the fortnight between having the photograph and having something that moves.

A commissioned product video
$500–$5,000

A commissioned product video

Typical turnaround
3–14 days

Typical turnaround

A month, for the AI tools in between
$23–$99

A month, for the AI tools in between

Fifteen seconds here, with sound
~$2.75

Fifteen seconds here, with sound

  • No studio day to book
  • No stock music licence to buy
  • No watermark to explain, on any tier
  • No surcharge for the vertical cut

What you put in

Four ways into a product film, depending on what you already have

The one thing that matters: the model re-renders everything in frame, including your product. Hand it the packshot as a reference and it stays close; describe the product and it invents one. Neither is your artwork — and the band after next is the workflow that fixes that.

  • Start from the packshot

    The shot you already paid for. Upload it and write what happens around it — the light, the hands, the move. Closest to the real product, and the route every example on this page took.

    Closest to your product · up to 9 images
  • Start from the whole range

    Nine reference images is a colourway run, not one hero shot. Same lighting, same move, one SKU swapped — which is how a catalogue gets shot in an afternoon instead of a week.

    Whole SKU line · 9 images, one rate
  • Start from an ad you like

    Give it a clip whose pacing works and your product still. It takes the camera moves and the cut points from the clip and the product from the image — two of the films above were made exactly this way.

    Borrow the edit · up to 3 clips
  • Start from nothing but words

    Useful for the concept, not for the catalogue: with no reference the model draws a product that looks like yours rather than one that is yours. Good for pitching a direction before the photography exists.

    Concept only · text to video

All four run on the same model at one rate — 8 credits a 768P second, 13 at 2K, plus 5 for the clip. References cost nothing extra. Every limit and rate, with the date each last changed.

Start to finish

How to make a product video in four steps

About four minutes end to end, most of which is you deciding what the product should do on camera. Nothing to install and nothing to sign before you see whether it works.

  1. A capsule coffee machine photographed on a kitchen counter, the frame that becomes the reference

    Upload the shot you already have

    The packshot is the single strongest instruction you can give. Send the cleanest frontal you own, and send the label, the colourway and the accessory as their own images — anything you do not attach is something the model gets to invent.

    Up to 9 imagesPackshot beats description
  2. Fruit and biscuits arranged on a saturated colour backdrop, surfaces sharply lit

    Name the material, not the mood

    Brushed aluminium, matte silicone, condensation on cold glass survives the render. Premium and modern does not — it produces a different product every take. Surfaces are what a camera actually photographs, so surfaces are what the prompt should name.

    Surfaces, not adjectivesOne material per clause
  3. A headphone advert mid-cut between a city panorama and a product close-up

    Emphasise modernity, simplicity and a tech feel; product close-ups cut against scene panoramas… the switching points stay consistent with the reference clip, so the cuts land on the beat.

    PictureSound

    Say what it sounds like

    Audio is generated with the picture, not laid under it afterwards — so the click of the cap, the pour, the fabric, the room it happens in are all written in the same field as the shot. Leave the music unspecified and the model scores the scene for you.

    One field, both channels
  4. A 3D animated grapefruit bursting into juice across a desert, the finished take
    Audio track · 32 kHzSKU-01.MP4

    Draft at 768P, master the keeper at 2K

    A 768P second is 8 credits against 13 at 2K, and upgrading a finished 768P clip afterwards costs exactly what rendering it at 2K would have — so the takes you throw away cost you less. A failed generation is refunded automatically.

    768P · 8 credits a second2K · 13 credits a second

Four steps, no install, no card. Open the generator.

The thing nobody tells you

It will not hand you back your product. Here is the workflow that fixes it.

Every page selling AI product video skips this, and you find out after the credits are gone. A diffusion model does not open your JPEG and move it. It draws a new frame twenty-four times a second, and a label it draws is a label it can get subtly wrong — a letter short, a logo half a degree off.
It matters less than it sounds, because most of a product film is not the product. Generate the fourteen seconds around it and put the real artwork on top.

  1. 01Generate the scene, composite the hero

    Write the room, the light, the hands and the sound, and leave a clean area where the product sits. Then drop your real packshot onto the layer above in whatever you already edit in. Two minutes, and the exactness problem is gone.

    your artwork, on the layer above

  2. 02Small type is where it breaks

    Ingredient lists, dosage panels, fine print on a carton. If the copy has to be legible and correct, it has to be composited — no video model is reliable at four-point type held for fifteen seconds.

    legible copy → composite

  3. 03There is no alpha channel

    What comes back is an MP4 with a 32 kHz stereo track. No transparent MOV, no ProRes 4444. If your deliverable is an overlay for someone else’s edit, render on flat black or flat white and let your editor key it.

    MP4 · 32 kHz · no alpha

  4. 04The marketplace has its own rules

    Amazon and Shopify both restrict what a listing video may claim and how it may be labelled, and several platforms now ask that synthetic media be disclosed. Generating the clip is the easy half; read the listing policy before you upload it.

    check the listing policy

  5. 05Land the cut on 8.000 seconds

    H3 renders on a 17n+5 frame grid at 24 fps, so most lengths come back a fraction long — 15s is really 15.083s. 192 frames, exactly 8.000 seconds, is the only whole second in the range, which makes it the length that cuts to music without drifting.

    192 frames = 8.000s

A fifteen-second product film at 768P is 125 credits, about $2.75. The same thing commissioned is a $500–$5,000 line item and three to fourteen business days.

Why this and not a template tool

A product film is a sound as much as it is a move

Watch a listing video with the audio off and it is a slideshow. The pour, the click, the fabric — that is what makes a viewer believe there is an object there. On most tools that is a second product, licensed separately and synced by hand.

  • Sound in the same pass

    The foley is written with the frame

    32 kHz stereo generated alongside the picture rather than laid under it, so the click happens on the frame the cap seats. No stock library, no licence, no sync pass.

  • One rate, six shapes

    The vertical costs what the wide does

    21:9, 16:9, 4:3, 1:1, 3:4 and 9:16 all bill at the same per-second rate, because the upstream bills per second and ignores the shape. A marketplace wants vertical and it costs you nothing extra.

  • Nine references

    A colourway run in one afternoon

    Nine images in one request is a range, not a hero shot: same light, same move, one SKU swapped. That cap is the number worth comparing against — most hosted doors onto this model do not publish theirs.

  • No subscription

    You pay for seconds, not for a seat

    There is no monthly floor here and nothing expires. The tools in this category start at $23 a month and run to $99 before you have rendered anything; this is 8 credits a second and a free one to start.

What you give up

Exactness, and alpha. You will not get your artwork back pixel-true, you cannot have a transparent MOV, and you cannot art-direct a single frame to the millimetre. If the deliverable is a marketplace hero video that gets checked against the physical product, generate the scene here and composite the real photography on top — that is the workflow this page recommends, not a workaround for it.

What it actually costs

A 15-second product film at 768P is 125 credits. About $2.75.

A clip is a flat 5 credits for the prompt-understanding pass, plus 8 credits per 768P second or 13 per 2K second. References are free — attaching nine product images costs the same as attaching none. One credit is one cent of MiniMax’s own published list price, so the whole thing can be checked against a page this site does not control. A generation that fails is refunded automatically, which matters when you are running a colourway at a time.

What a product film costs, by length

One 4s loop, 768P
37 credits
One 8s film, 768P
69 credits
One 15s film, 768P
125 credits
One 15s film, 2K
200 credits
Six SKUs at 8s, 768P
414 credits
Six SKUs at 8s, 2K
654 credits

Full pricing · every limit and rate, dated · what a 2K second really costs

Same monthly credits either way

  • FreeNo card

    One real MiniMax H3 clip, with sound. Everything past 4s · 768P runs on credits.

    $0forever

    No credit card at any point

    Start free

    Bot check only — no email

    1 clip on MiniMax H3

    MiniMax H3 · 4s · 768P · 16:9 · with sound
    Check in 7 days — 37 credits, one more clip

    Any pack from $9.9 unlocks the MiniMax H3 AI video generator — every mode, 768P and 2K

    • MiniMax H3 at native 2KPaid only
    • Native audio with the picturePaid only
    • One clip, no card
    • 1 clip at a time
    • Failed clips cost nothing
    • Private generation
    • Any pack unlocks the MiniMax H3 AI video generator on every mode

    Free is a different engine. See plans

    Speed & queue

    Queue
    Free lane
    Jobs at once
    1
    Batch
    1
    History kept
    24h · 7 days signed in
    Support
    Community
  • LiteSave 30%

    Unlock the MiniMax H3 AI video generator at native 2K. The smallest paid plan — Pro is the one most people pick.

    $16.9/mo$24.9

    $202.8 billed yearly · Save $96 a year

    7-day refund · cancel anytime

    750 credits / month · ~20 videos

    4s · 768P · text to video

    or ~13 at 4s 2K

    Same credits monthly or yearly

    • MiniMax H3 at native 2K — with native audio
    • Dialogue, effects and music in the same file
    • Up to 15 seconds15s
    • ~20 videos a month at 4s 768P, text to video
    • Failed clips cost nothing
    • 7-day refund if credits are unused
    • 1 job at a time
    • Batch 2 variants of one prompt

    Commercial use included — what that covers

    Speed & queue

    Queue
    Standard
    Jobs at once
    1
    Batch
    2
    History kept
    7 days
    Support
    Email · 48h
  • Recommended for most
    ProSave 30%

    $32 more than Lite. ~47 videos a month, same MiniMax H3 AI video generator, faster queue.

    $39.9/mo$56.9

    $478.8 billed yearly · Save $204 a year

    7-day refund · cancel anytime

    1,775 credits / month · ~47 videos

    4s · 768P · text to video

    or ~31 at 4s 2K

    Same credits monthly or yearly

    • Everything in Lite
    • ~47 videos a month at 4s 768P, text to video
    • 3 jobs at once
    • Video-to-prompt
    • Batch 4 variants of one prompt
    • History kept for 7 days
    • 7-day refund if credits are unused

    Commercial use included — what that covers

    Speed & queue

    Queue
    Fast
    Jobs at once
    3
    Batch
    4
    History kept
    7 days
    Support
    Email · 12h
  • StudioSave 30%

    A full month of volume, first in line, and a human who answers in 4 hours.

    $99.9/mo$142.9

    $1,198.8 billed yearly · Save $516 a year

    7-day refund · cancel anytime

    4,425 credits / month · ~119 videos

    4s · 768P · text to video

    or ~77 at 4s 2K

    Same credits monthly or yearly

    • Everything in Pro
    • ~119 videos a month at 4s 768P, text to video
    • 8 jobs at once
    • Batch 4 variants of one prompt
    • History kept for 7 days
    • Priority support in 4 hours
    • Lowest credit burn we offer
    • 7-day refund if credits are unused

    Commercial use included — what that covers

    Speed & queue

    Queue
    Priority — first in line
    Jobs at once
    8
    Batch
    4
    History kept
    7 days
    Support
    Priority · 4h

Can you actually run it

Yes, commercially — including on the free one

A listing video is a commercial document, so here is the rights position before you spend anything.

  • Commercial useThe free one as well. No watermark on any tier, no per-clip royalty, no separate licence to buy. MiniMax claims no rights over the Outputs you generate, and this site adds none of its own.
  • Your own productUploading your packshot as a reference does not hand it to anybody. It stays yours, and whatever comes back is yours to put on a listing, in an ad, or on the shelf edge.
  • What you may claimA generated demonstration is a dramatisation. Showing a product doing something it cannot do is a claim, and the rules that govern advertising claims do not change because a model drew the frame. Keep the performance honest.
  • Somebody else’s brandNothing here grants you rights in a trademark you do not own, and a competitor’s product in your frame is a problem no matter how it got there. Run the same clearance you would run on a photograph.

Responsible use in full

Before you spend anything

AI product video generator FAQ

The eight questions people ask before putting a generated clip on a listing, answered with the numbers behind them.

Is this AI product video generator free?

The first clip is, and it is the real model — 4 seconds, 768P, with sound, no watermark, no card, and it never expires. Everything on this page plays without an account. After that an 8-second film is 69 credits and a 15-second one is 125; credits start at $9.9, which puts a full film at about $2.75. A generation that fails costs nothing.

Will it use my exact product?

Close, not exact. Upload the packshot as a reference and the shape, colour and finish come back recognisable — but the model redraws every pixel, so a label can come back a letter short. For a marketplace hero video, generate the scene here and composite your real photography on the layer above. It takes about two minutes and it is what the band above recommends.

Can I get a transparent background?

No. What comes back is an MP4 with a 32 kHz stereo track — no transparent MOV and no ProRes 4444. If you need an overlay, render on flat black or flat white and key it in your editor.

Can I do a whole colourway or SKU line?

Yes, and it is the cheapest thing on this page. Nine reference images in one request holds the light and the move while the product changes, so six SKUs at eight seconds is 414 credits — about $9 for the set. References cost nothing extra; you pay for seconds.

Does it come with audio, or do I add music afterwards?

It comes with audio. 32 kHz stereo is generated in the same pass as the picture, so the foley lands on the frame the action happens. Name the click, the pour and the room; leave the music unspecified and the model scores the scene. There is no stock licence to buy.

What lengths and shapes can I get?

4 to 15 whole seconds at 24 fps, at 768P or 2K, in 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16 — all at the same per-second rate, so the vertical cut a marketplace wants costs no more than the wide one. There is no 1080p output: 768P then 2K.

Can I put this on an Amazon or Shopify listing?

From our side, yes — commercial rights are included on every plan and there is no watermark. From theirs, each marketplace sets its own rules on what a listing video may show and claim, and several platforms now ask that synthetic media be disclosed. Read the listing policy; a generated demonstration is a dramatisation, not a proof.

How is this different from a template product video maker?

A template tool drops your photo into a motion preset somebody else designed, and charges $23 to $99 a month for the library. Here the structure is the sentence you wrote, the audio is generated with the picture, and you pay 8 credits a second with no monthly floor. Worse if you want a hundred presets; better if you want one film that looks like your brand and not like the preset.

Stop describing the product. Show it moving.

One packshot, one sentence about the move and the sound, and a finished clip in about ninety seconds. Your first one is free — no card, no watermark, and it is yours to use commercially.

Sign up free · 1 clip on MiniMax H3

Written and maintained by the MiniMax H3 AI Video Generator editorial teamPublished Last updated Tool version 2026.09.4