Skip to main content
Get started free

Etsy Listing Videos With AI: Specs, Rules, and Costs

Etsy takes two listing videos of 5 to 15 seconds with the audio stripped. The exact specs, what its policy allows for AI video, and the credit cost per clip.

Etsy Listing Videos With AI: Specs, Rules, and Costs

Etsy accepts up to two listing videos per listing, 5 to 15 seconds long, 100MB or smaller, and it strips the audio on upload (etsy.com, July 2026). AI video is allowed. One rule decides whether yours survives: the listing has to show the actual finished item the buyer receives, not a rendering. Start from a photo of your real product and you stay inside that rule.

Most guides to Etsy listing videos with AI stop at the specs. Specs are the easy half. The half that gets shops removed is Etsy’s Listing Image Requirements policy, which says sellers must use their own photos or video of the actual finished product, not renderings or stock photos (etsy.com, July 2026).

That single line is the difference between a video that runs for years and a listing that gets pulled. It also rules out the most common way people use AI video: typing a description of a product and generating a clip of something that looks like it.

This covers Etsy’s real specs, what its policy does and does not allow, the three places the platform breaks a normal AI video workflow, and what a compliant clip costs.

Key Takeaways

  • Two videos per listing, 5 to 15 seconds, 100MB max. Etsy’s help page states 3 to 15 seconds while its Listing Image Requirements policy states 5 to 15. Build to 5 to 15 and you clear both (etsy.com, July 2026).
  • Etsy deletes your audio. Videos do not play sound once uploaded. Paying for a model with native audio generation is money Etsy throws away.
  • The video must show the real item. Etsy requires your own photo or video content of the actual finished product. Generating a product that does not exist is the fastest way to lose a listing.
  • Aspect ratio is 2:1 or 1:2, which no video model outputs natively. Generate 16:9 or 9:16, then crop before upload.
  • AI disclosure applies to the item, not the camera. Etsy requires disclosure when an item is created through AI. A real handmade item filmed or animated with AI is a different question from an AI-generated product.
  • A 15-second clip runs 450 credits at the cheapest model rate, so a Premium plan at 2,500 credits covers roughly five full-length listing videos a month.
  • Stills are far cheaper than video on Etsy. Twenty listing photos cost 100 credits. One 15-second video costs four times that.

What are Etsy’s listing video requirements?

Etsy allows up to 20 photos and 2 videos on each listing. Videos run 5 to 15 seconds, cap at 100MB, and lose their audio track when published. The minimum resolution is 500px and the ideal is 1080px or better. Etsy’s help documentation gives the aspect ratio as 2:1 or 1:2 (etsy.com and help.etsy.com, July 2026).

SpecEtsy’s requirement
Videos per listingUp to 2
Photos per listingUp to 20
Length5 to 15 seconds
AudioStripped on upload, always silent
Max file size100MB
Minimum resolution500px
Ideal resolution1080px or higher
Aspect ratio2:1 or 1:2

One inconsistency is worth knowing before you produce anything. Etsy’s help article on adding listing videos gives the length as 3 to 15 seconds. Its Listing Image Requirements policy gives it as 5 to 15 seconds. Both are Etsy’s own pages and they disagree by two seconds at the bottom end. Produce at 5 seconds or longer and the conflict never touches you.

Can you use AI video on an Etsy listing?

Yes, with a constraint that most guides skip. Etsy’s Listing Image Requirements policy says sellers must use their own photos, either taken by them or for them, showing the actual finished product they made, designed, handpicked, or sourced. Renderings and stock photos are prohibited. Listings for items made by a seller must use original photo or video content of the final product (etsy.com, July 2026).

Read that against how AI video usually works and the line becomes obvious. A text prompt that generates a ceramic mug produces a mug that does not exist. That is a rendering of an invented product, and it fails the policy no matter how good it looks.

A photo of your actual mug, animated into a 10-second turntable, is a different object entirely. The source is your real finished item. The camera move is synthetic. The product is not.

That distinction is the whole game on Etsy, and it is why generating from your own product photo is the only workflow worth building. Every asset traces back to a photo of a thing that exists in your studio.

What about the AI disclosure rule?

Etsy’s Seller Policy requires disclosure when an item is created through the use of artificial intelligence (etsy.com, July 2026). Its Creativity Standards recognise seller-prompted AI art under the “Designed by a seller” category, where the seller directs the work and is transparent about the process.

The rule attaches to the item, not to the equipment. A hand-thrown bowl is not an AI creation because you used AI to light the photograph of it. An AI-generated digital print you sell as a download is an AI creation and needs disclosing.

Where the two overlap, disclose. Etsy’s Creativity Standards ask for transparency about the process and for machine output not to be presented as handmade. If you are unsure which side your product sits on, the safe move costs you a checkbox.

Etsy is stricter here than most marketplaces, and the rules diverge sharply once you sell across several. For the side-by-side, see what each marketplace requires for AI product images. The same rule shapes the stills, and Etsy product photos covers what it leaves you to shoot and what it leaves you to edit.

One exception for personalised items

Etsy carves out a narrow allowance for personalised and customised products. The first image must show a finished, customised item close to what buyers receive. Computer-generated mockups are permitted in the additional images to show customisation options (etsy.com, July 2026).

The exception is real but small. It applies to extra images demonstrating variants, not to the lead asset, and not as a way around the actual-product rule.

Where Etsy breaks a normal AI video workflow

Three platform decisions make Etsy different from TikTok, Reels, or a product page you control.

Etsy deletes the audio. Listing videos never play sound. Etsy’s own guidance tells sellers not to bother removing background noise because the platform strips it anyway. Models that generate native audio charge a large premium per second for it, and on Etsy that premium buys a track nobody hears. Pick a silent model and spend the difference on more clips.

The aspect ratio does not match any model. Video models output 16:9 or 9:16. Etsy asks for 2:1 or 1:2. Neither native ratio lands there, so every clip needs a crop before upload. Frame with margin around the product so the crop does not cut it in half.

Fifteen seconds is a ceiling, not a target. Plenty of listing videos work at 5 or 6 seconds. A single loop showing scale, texture, and one angle change answers the question a shopper has. Generating the full 15 seconds triples the credit cost for time most shoppers never watch.

How to make an Etsy listing video from one product photo

The workflow is short because the constraint is short. Everything starts from a photo of the real item.

  1. Shoot one clean still of the finished product. A phone on a windowsill is enough. This photo is your compliance anchor and the input to everything downstream.
  2. Clean the still first. Fix the background and the lighting before any motion. Errors in a still get multiplied across every frame of the video.
  3. Animate the still, do not describe the product. Feed the photo into an image-to-video model so the output is your object moving, not a lookalike generated from text. Turning a product photo into a video ad follows the same path.
  4. Keep the camera move small. A slow orbit, a push in, a hand entering frame to show scale. Big motion is where AI video shows its seams on textured handmade goods.
  5. Generate at 5 to 10 seconds. Cheaper than 15, and long enough for one clear idea.
  6. Crop to 2:1 or 1:2 and export under 100MB. Check the file size before you upload rather than after Etsy rejects it.
  7. Add a second video for a different angle. Etsy gives you two slots. Most sellers use one.

Models differ on how well they hold texture through motion, which matters more for handmade goods than for hard-edged consumer products. Seedance 2.0 handles multi-reference input and longer durations. The wider approach to animating a still for ecommerce applies whichever model you pick.

What an Etsy listing video costs in credits

DesignerBox prices video by credits per second of output, so cost scales with length rather than with the number of tries. At the cheapest model rate, a 5-second clip is 150 credits and a 15-second clip is 450.

Clip lengthCheapest model rateMid-tier model rate
5 seconds150 credits225 credits
10 seconds300 credits450 credits
15 seconds450 credits675 credits

Against the monthly allocations, that math is easy to run. Premium includes 2,500 credits a month, which covers roughly five 15-second listing videos or sixteen 5-second ones. Ultra includes 8,000 credits, or about seventeen full-length clips.

Two limits are worth stating plainly. AI video generation requires the Premium plan at $75 a month or higher, so it is not available on Basic or Pro. And the free plan’s 112 credits will not cover a single 5-second clip, though it does cover 22 image generations at 5 credits each.

Stills are the better deal on Etsy by a wide margin. Twenty listing photos cost 100 credits total. One 15-second video costs 450. For a shop with 60 listings, filling every photo slot is affordable and filling every video slot is not, which is an argument for putting video only on the listings that already get traffic. The full credit breakdown per plan shows where the line sits for your catalogue size, and affordable AI video for product listings compares the same math across other marketplaces.

Which listing videos earn the click

Etsy’s own seller guidance points at three formats that shoppers respond to: the product in use, the details a photo flattens, and the making of the item.

Scale and proportion. A hand picking up the item resolves the question every static photo leaves open. This is the single highest-value shot for jewellery, ceramics, and anything small.

Texture under moving light. Glaze, grain, weave, and stitch read as flat in a still. A slow light sweep across the surface shows what the buyer is paying for.

Angle change. A quarter turn covers what three separate photos would. On a 15-second budget this is the most information per second available.

Skip the lifestyle montage. A silent 8-second clip of the actual object beats a cinematic sequence that never shows the product clearly, and it costs a fraction as much to generate. Shooting product video without a studio works on the same principle.

What gets an Etsy listing video removed

The failure modes are consistent and all trace back to one rule.

  • Generating the product from text. The output is a rendering of an item that does not exist. This is the clearest policy violation available.
  • Adding features the real item does not have. Enhancing a photo is fine. Adding a gemstone, changing a colourway, or smoothing a flaw into something the buyer will not receive misrepresents the item.
  • Using stock or another seller’s footage. Etsy prohibits both regardless of how the footage was made.
  • Leading a personalised listing with a mockup. The first asset has to be a finished customised item. Mockups belong in the additional slots.
  • Selling an AI-created item without disclosure. The item, not the photography, triggers the requirement.

Every one of these is avoided by the same discipline: the clip starts from a photo of the finished thing, and the AI changes how it is shown rather than what it is.

Bringing it into one workflow

An Etsy shop with a monthly drop needs the same set every time. Clean stills for the 20 photo slots, one or two short videos, and a matching set for the social post announcing it. Producing that across separate tools means separate bills and a different look from each one.

DesignerBox runs it from the single product photo you already shot. Image models clean and reframe the stills, video models animate the same source, and the outputs land in one library. Save the sequence as a workflow and rerun it on the next product instead of rebuilding it. Photo Studio is where that lives for product listings specifically.

The real cost of the alternative is not the subscriptions. It is the seams.

The product video generator runs a first listing clip free.

FAQ

How long can an Etsy listing video be?

Etsy listing videos run 5 to 15 seconds. Etsy’s help article states 3 to 15 seconds while its Listing Image Requirements policy states 5 to 15 (etsy.com, July 2026). Producing at 5 seconds or longer satisfies both. The maximum file size is 100MB and the ideal resolution is 1080px or higher.

Does Etsy allow AI-generated listing videos?

Etsy allows AI video as long as the listing shows the actual finished product the buyer receives. Etsy’s Listing Image Requirements policy prohibits renderings and stock photos and requires sellers to use their own photo or video content of the final product (etsy.com, July 2026). Animating your real product photo complies. Generating a product from a text description does not.

Do Etsy listing videos have sound?

No. Etsy strips audio from listing videos on upload, and they always play silent. Etsy tells sellers not to worry about removing background noise for this reason. Any model feature that generates native audio is wasted spend for an Etsy listing.

How many videos can you add to an Etsy listing?

Two. Etsy allows up to 20 photos and 2 videos per listing. Most sellers use one video slot, so the second is free coverage for a different angle or a scale shot.

Do I have to disclose that I used AI on my Etsy listing?

Etsy’s Seller Policy requires disclosure when an item is created through the use of artificial intelligence (etsy.com, July 2026). The rule attaches to the item rather than to the tools used to photograph it. An AI-generated digital download needs disclosure. A handmade item photographed with AI assistance is a separate question, and disclosing when unsure carries no downside.

What aspect ratio should an Etsy listing video be?

Etsy’s help documentation gives the video aspect ratio as 2:1 or 1:2 (help.etsy.com, July 2026). Video models generate at 16:9 or 9:16, so plan on cropping every clip before upload. Leave margin around the product when framing so the crop does not cut into it.

What does an AI listing video cost?

At the cheapest model rate, a 5-second clip costs 150 credits and a 15-second clip costs 450. DesignerBox’s Premium plan includes 2,500 credits a month, covering roughly five full-length listing videos. AI video generation requires Premium at $75 a month or higher.

Sources

All accessed July 2026.

  • Listing Image Requirements: the rule that listings must use the seller’s own photo or video of the actual finished product, the prohibition on renderings and stock photos, the personalised-item mockup exception, the Seller Policy AI disclosure requirement, and the Creativity Standards “Designed by a seller” category: (etsy.com, July 2026)
  • Listing video specifications: two videos and 20 photos per listing, the 5 to 15 second length (with the help article’s conflicting 3 to 15), the 100MB cap, the 500px minimum and 1080px ideal resolution, the 2:1 or 1:2 aspect ratio, and audio being stripped on upload: (help.etsy.com, July 2026)
  • DesignerBox pricing, credit costs, plan allocations, model catalogue and feature gating verified against live product configuration, July 2026

Etsy listing video specifications, Listing Image Requirements, Creativity Standards, and Seller Policy verified from etsy.com and help.etsy.com as of July 2026. Etsy’s own pages give conflicting minimum video lengths and are quoted as published. Individual results vary.

Vytas

Founder at DesignerBox

Vytas is a founder at DesignerBox, from the team behind LoadFocus, FocusBox and PostNext. He writes about turning one product photo into a full campaign, and the pipelines that keep every asset on brand.

Follow along on Instagram at @designerboxai for campaign breakdowns.

Every top video model, one bill

Veo 3.1, Sora 2 Pro, Kling 2.6 Pro, Seedance 2.0 and Runway Gen-4.5 are built in. Switch models per shot without a second subscription or a second login.

Start free

Upload one product photo. Ship the whole campaign, without a photoshoot.