Open navigation menuClose navigation menu

Open your PDF in 3D

Open a manual, protocol, or spec in 3D and have Scholarly's AI build a labelled model of what it explains. Turn it around, refine it in chat, and export it for slides and video.

Sign up for freeHow 3D models work

Beta. A full AI build uses 1 AI Creation Credit, and you confirm it first. Small chat edits are free.

A labelled 3D model built from a PDF in Scholarly, with the chat beside it

Quick answer

What does Scholarly's 3D PDF viewer do?

Updated October 2026 · 3D models are in Beta

It opens an ordinary PDF in 3D: the PDF's first pages appear in the scene, and the chat beside it builds a 3D model of what those pages explain. Scholarly's AI writes the model as real three.js code, with geometry, materials, lighting, labels from the source, and animation where it helps. You orbit and zoom, switch views, and export on a paid plan. It does not open the embedded 3D content (U3D or PRC) found in engineering 3D PDFs.

People mean two things by "3D PDF". One is an engineering file with an embedded CAD model, which needs Adobe Acrobat or a CAD viewer. The other is a document that explains something physical, an infusion pump, a heart valve, a cloud architecture, a gear train, where you would rather see the thing than read about it. Scholarly does the second.

Open the PDF in 3D, then ask for the model. The AI reads the first pages and builds what they describe, so the labels say what your document says. Because the model is real three.js code, it can be a plant cell cut away to show its organelles with leader lines and readable labels, or a gear train that actually turns.

From there it is ready to use. Orbit it, switch between perspective, front, side, and top views, or start a turntable. On a paid plan, export a 4K PNG, a transparent PNG for a slide, an 8-second 1080p turntable video, or a .glb file that opens in PowerPoint, Keynote, Blender, and web 3D viewers.

How it works

How to open a PDF in 3D

Open the PDF, ask for the model, preview the draft, then use it.

  1. 01

    Open a PDF

    Choose one from your library or upload it. Its first pages appear in 3D.

  2. 02

    Ask for a model

    In the chat, say what the model should show, then confirm the build. A full build uses 1 AI Creation Credit.

  3. 03

    Preview and apply

    After a few minutes, preview the draft and apply it, or keep your current model.

  4. 04

    Refine and export

    Make free small edits in chat, then export an image, a turntable video, or a .glb on a paid plan.

Use cases

Why open a PDF in 3D

Some documents explain things that are easier to see than to read.

Equipment manuals

See how a device or a trades unit fits together, each part labelled from the manual.

Slides and presentations

Export a transparent PNG for a slide, or a .glb you can drop into PowerPoint or Keynote.

Clinical and anatomy reading

Turn an anatomy chapter or a nursing protocol into a labelled cutaway you can rotate.

Architecture docs

Model an IT or cloud architecture from its design doc, one tier above the next.

Training videos

Export an 8-second 1080p turntable MP4 to drop into a training or onboarding video.

Engineering explainers

Show how a mechanism works with an animated model, such as a gear train that turns.

Try asking

Things to ask the chat

A new model is a full build. Wording, colour, size, animation speed, and background changes are free small edits.

  • Build a 3D model of the device these pages describe, with every part labelled.

  • Make a cutaway so the inside is visible, with leader lines to each part.

  • Slow the animation down by half.

  • Change the label "Valve" to "Pressure relief valve".

  • Make the background white for a slide.

  • Colour the parts the manual calls critical in red.

Beta

What it can and can't do today

3D models are in Beta. Here is what the viewer does, and what it doesn't.

Works today

  • Opens ordinary PDFs; the first pages appear in 3D and the model is grounded in what they say.
  • Real three.js geometry, physically based materials, lighting, and animation.
  • Orbit and zoom, perspective, front, side, and top views, frame all, and a turntable.
  • On paid plans, export a 4K PNG, a transparent PNG, an 8-second 1080p turntable MP4, or a .glb file.

Not supported

  • Not CAD-accurate or engineering-grade. Models explain how something works; they are not measured designs.
  • No STL or OBJ export, and no 3D printing. Exports are images, a turntable video, and a .glb file.
  • No manual 3D editing tools: no sculpting and no dragging parts. You change a model by asking chat.
  • A model starts from one PDF or from an empty chat. For notes or slides, save them as a PDF, or describe the content in chat.
  • It's a Beta: preview every draft before you apply it, and check the labels before a model goes in front of a team.

FAQ

Frequently asked questions

Can it open 3D PDFs with embedded CAD models (U3D or PRC)?

No. Those files carry an embedded 3D model that needs Adobe Acrobat or a CAD viewer. Scholarly opens an ordinary PDF in 3D and builds a new explanatory model from what its pages say.

Which pages does it use?

The PDF's first pages appear in 3D, and the model is built from what they say. For a longer document, save the section you want as its own PDF.

How can I look at the model?

Orbit and zoom, switch between perspective, front, side, and top views, use frame all to fit the whole model, or start a turntable.

Does it use credits?

Opening a PDF in 3D and small chat edits (a label's wording, a colour, a size, an animation's speed, the background) are free and appear on an approval card. A full build uses 1 AI Creation Credit, and you confirm it before it starts. You can sign up for free.

Do I need to install anything?

No. It runs in your browser with three.js, and the model saves to your Scholarly workspace. Undo brings back the previous version.

Can I use the model in PowerPoint, Keynote, or a video?

Yes, on a paid plan. Export a 4K PNG, a PNG with a transparent background, an 8-second 1080p turntable video (MP4), or a .glb 3D file that opens in PowerPoint, Keynote, Blender, and web 3D viewers. There is no STL or OBJ export and no 3D printing.

Open a PDF in 3D

Sign up, pick a PDF, and have AI build a model of what it explains.

Sign up for freeHow 3D models work

Beta. A full AI build uses 1 AI Creation Credit; small chat edits are free. Exports need a paid plan.