The Tashvi Alternative for Working Jewelers (2026)

Jewelers go looking for a Tashvi alternative for one of two reasons: they want real control over the design, or they want a file they can make, photograph, and sell. Ruby Kinglet is built for both. Tashvi keeps its place for quick, cheap concept images.

Ruby Kinglet is ours: the builder that carries a design into CAD, photos, and a storefront. Updated September 2026. Pricing for both tools is from their own pricing pages as of that date.

The design itself: how far down the controls go

Tashvi has a guided mode where you set the setting type, stone shape, metal, and accent stones, and an agent mode that refines a design over several turns. Ruby Kinglet's builders go further into the piece: settings, stones, and metals are separate editors with their own libraries, so every design comes out specific and repeatable.

The specificity is countable. More than 700 built-in jewelry components, including over 300 gemstone species and varieties, so you pick an Asscher or a bezel-set trilliant by name. Metals run from bases through satin, brushed, engraved, and anodized finishes. An illustrated setting library covers prong styles, head styles, shank profiles, galleries, halos, setting methods, chain types, closures and earring backs. The angle library holds hundreds of camera positions, drawn separately for rings, earrings, necklaces, and bracelets. A GIA Graduate Gemologist built the gemstone libraries. None of that falls out of a general image model.

The library also grows on its own. Jewelers share trained models and templates, so the library you start from carries other jewelers' work alongside ours, and Ruby Kinglet's design competitions with published themes feed a lot of it. A prompt box has nothing to accumulate, and an enterprise product has no reason to let customers contribute to each other.

On top of the builders sits an AI Studio with more than 20 jewelry-specific editing tasks: swap stones and metals, adjust settings and findings, edit a small detail, add an inscription, control reflections and angles, remove an artefact, pair a piece with inventory stones. Each is its own tool with its own controls. Around that sit three things a prompt tool has no equivalent for. Mood boards attach a directive to each reference image, “use this silhouette,” “swap to rose gold,” so the reference becomes an instruction. Your own libraries hold components you upload and reuse. And more than 6,000 community templates bootstrap a complex piece.

Training closes the loop. Train AI models on your own portfolio and use them across the builders, the AI Studio, photoshoots, and the rest of the platform, so what comes out reads as your work, with none of the generic luxury look every general model drifts toward. The tool accumulates your practice session after session.

What that buys: complex work

The payoff is complexity. A prompt-driven tool is reliable on simple, symmetrical, conventional pieces, which is why so much AI jewelry looks like the same halo solitaire. It gets vague where jewelry gets interesting: an asymmetric setting, a mixed-cut cluster, an unusual gallery, a piece where the back matters as much as the front. Those need specified parts, a way to edit one element without disturbing the others, and something to start from. The builders, the 20-plus tasks, the templates, and your own libraries deliver exactly that.

Ruby Kinglet has been in development since 2022, and the founding team includes a bench jeweler, a GIA gemologist, and machine learning specialists who have led AI teams in San Francisco and Singapore. It shows in the vocabulary: the software knows what a gallery is, what a knife-edge shank is, what setting method a given stone wants. Software written outside the trade models jewelry as a shiny object. Software written inside it models jewelry as parts.

Work without a credit counter

Jewelers notice the limits first. Tashvi meters every generation by credit on paid plans at $20, $60, and $200 a month, or $16, $48, and $160 billed annually. Ruby Kinglet has no credit balance to buy and burn down and nothing metered on screen. Personal and Professional have a monthly cap and Studio has none.

Metering changes how you work before you have done anything. With credits you decide whether a variation is worth spending on before you try it, and that decision shapes the output: you stop at good enough because the next attempt has a price on it. Take the counter away and you just try it. Trying an idea ten different ways is the job, and the tenth version is usually the one that ships. On Professional and above the ceiling never enters your head, because a creative tool you are rationing is a creative tool working against you.

From the image to a piece you can sell

The design carries past the image. It connects to CAD, with STL and mesh creation per design and 3DM generation on the Studio plan, to a full photo studio for product shots, and to a storefront customizer a customer can order from. All four share one workspace, so a model trained on your portfolio for design also shapes the imagery. Tashvi's output is a design image plus an STL export, and it stops there. For most jewelers the stretch from a good render to a piece you can make, photograph, and sell is the whole job.

On the CAD-ready claim

Tashvi lists STL export on paid plans and still describes advanced CAD export as in development. An STL is a frozen mesh: a surface you can print or mill but not edit, resize, or rebuild by part. Most image-to-3D tools hand you exactly that, a single black-box mesh, far from a file a bench can work with.

Ruby Kinglet treats this as real CAD work, split into two jobs. Swappable parts is for renders: take one 3DM and render it many ways, swapping metals, stones, and settings with the geometry intact. That is how you build a showcase range for a website, let a shopper customize the stones, or sell one design in several metals without re-shooting anything. Editing a 3DM starts from a file you already have and edits it into a new piece, so new work bootstraps off past work. Both run on a Rhino parametric engine with jewelry-specific libraries, so the geometry respects how a piece is built. 3DM editing covers engagement rings and the common styles today. STL work sits alongside: photo to a printable, manufacturable mesh with a thickness check, and castable component parts you can compose into a 3DM, well beyond a generic image-to-STL step.

Test any AI-generated file against your own manufacturing before you rely on it, from any tool, ours included. A render that looks right and a file that casts clean are two different things.

Side by side

Where Tashvi still fits

Tashvi has a free plan with limited generations and no card, and paid plans at $20, $60, and $200 a month ($16, $48, and $160 billed annually). For a quick concept image to show a client or post to social, with nothing downstream, Tashvi does the job cheaply.

The pick

Choose Ruby Kinglet if your pieces are more particular than a prompt can hold, if you want the tool to accumulate your components, templates, and a model trained on your own work, and if the design has to become something you can manufacture, photograph, and sell. Do the arithmetic on that last part before comparing monthly prices: a design image is the first of four steps, and a tool that stops there leaves you paying for CAD, photography, and a storefront configurator separately, with a handoff at each seam. We compare the three head to head in Tashvi vs BLNG vs Ruby Kinglet.

Choose Tashvi if you want low-cost design images of fairly conventional pieces and nothing downstream. Many jewelers run a fast image tool for a first pass and Ruby Kinglet for the work that ships, and that setup works.