Turn training docs into interactive 3D explainers
Open a manual, equipment guide, or product spec, and Scholarly's AI builds a labelled 3D model of what it explains. Export it as an image, a turntable video, or a .glb for your PowerPoint and Keynote decks.
Beta. A full AI build uses 1 AI Creation Credit, and you confirm it first. Small chat edits are free.
Quick answer
How do I make 3D training materials without a 3D artist?
Updated October 2026 · 3D models are in Beta
Open the training document as a PDF in Scholarly and ask the chat to build a 3D model of what it explains: a device's parts, a machine's assembly, a system's tiers. Scholarly's AI reads the pages and writes the model as real three.js code, with geometry, physically based materials, lighting, labels from the document, and animation where it helps. You preview the draft and apply it, then export a 4K PNG, a transparent PNG, a 1080p turntable MP4, or a .glb on a paid plan. No 3D software or modelling skills are needed.
3D training content usually means a vendor, a 3D artist, and weeks of back-and-forth, so most teams settle for screenshots and slides. For explaining how equipment or a product is put together, a labelled model gets most of the value: learners see where each part sits and connect names to positions, whether it's an infusion pump, a heat pump, or a server rack.
Grounded in your documentation. The AI reads the manual or guide before it builds, so part names, module names, and labels match what your docs say. A subject-matter expert previews the draft, applies it, and fixes a label's wording or a colour with free chat edits, without a ticket to a design team.
It goes straight into the rest of the programme. Drop a 4K or transparent PNG into a slide, cut the 8-second turntable MP4 into a training video, or open the .glb in PowerPoint or Keynote. In Scholarly the same source PDF can also become a narrated training video, a quiz, flashcards, or a study guide.
How it works
From training document to 3D explainer
Your documentation in, a reviewed model out, ready for slides and video.
- 01
Open the training document
A manual, equipment guide, spec sheet, or course pack, opened as a PDF. Its first pages appear in 3D.
- 02
Ask for an explainer model
Name the product, machine, or system and what learners need to see, then confirm the build, which uses 1 AI Creation Credit.
- 03
The AI builds the model
Over a few minutes it reads the document and writes the model in three.js, with labelled parts, materials, lighting, and animation.
- 04
Expert review, then export
A subject-matter expert previews the draft, applies it, refines it in chat, and exports it for slides or video on a paid plan.
Use cases
Training that benefits from a model
Anywhere learners need to know where things are and how they fit.
Product training
A product's modules or components, labelled from the product guide.
Sales enablement
How your platform fits together, so reps can explain it with confidence.
Clinical equipment onboarding
The parts of a monitor, pump, or ventilator, named the way the manual names them.
Trades and field training
The HVAC, electrical, or mechanical equipment technicians service, labelled and cut away.
Safety training
Where hazards, controls, and checkpoints sit in a process or a space.
IT and cloud training
A cloud architecture or network, tier by tier, built from the internal doc or the official study guide.
Try asking
Requests for training models
Point the AI at the pages that matter and name what learners must notice.
Build a 3D model of the product's modules from this product guide.
Label every part named in the parts diagram on page 7.
Show the three service tiers one above the next, with the components in each.
Make the safety-critical parts red.
Animate the fan and the belt so learners see what moves.
Rename the labels to the terms our support team uses.
Beta
What it can and can't do today
3D models are in Beta. For training teams, here's the scope today.
Works today
- Builds from one training PDF, grounded in its pages, or from a description in chat.
- Real three.js geometry, physically based materials, lighting, and animation, with part names from your docs.
- Experts preview every draft before it's applied; Undo brings back the previous version.
- 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.
For teams
Built for training teams
Scholarly Teams is a shared workspace for this work: a shared source library, Owner, Admin, and Member roles, activity reporting, and one Stripe bill. Your manuals and guides live in one place, and the people building training, from L&D to enablement to product marketing, work from the same documents.
Premium Teams is $35 per seat per month and Laureate Teams is $110, self-serve for 1 to 29 seats. 3D models are in Beta; export them as images, turntable videos, or .glb files for the decks and videos your team already ships.
FAQ
Frequently asked questions
Do I need 3D modelling skills?
No. You describe the model in plain language and Scholarly's AI builds it. There are no manual 3D editing tools to learn: you change a model by asking chat, and small edits are free.
Can I use the model in our slides, videos, or LMS?
Yes, through exports on a paid plan: a 4K PNG, a PNG with a transparent background, an 8-second 1080p turntable video (MP4), and a .glb 3D file that opens in PowerPoint, Keynote, Blender, and web 3D viewers. Put those in the decks, videos, or courses your LMS already hosts. There is no SCORM package.
Is it CAD-accurate or a photoreal replica?
No. Models use real geometry, physically based materials, and lighting, but they are explanatory models, not CAD-accurate or engineering-grade replicas. There is no STL or OBJ export and no 3D printing.
What documents work?
Any PDF: manuals, equipment guides, SOPs, course packs, spec sheets. Word files, Google Docs, and slide decks work once saved as PDF. The PDF's first pages appear in 3D and the model is built from what they say.
How does pricing work for a team?
A full build uses 1 AI Creation Credit, and you confirm it first. Small chat edits are free. Exports need a paid plan. Team seats draw on their plan's credits, and Owners and Admins can buy more on the team bill.
What else can I make from the same manual?
Narrated training videos, quizzes, flashcards, SOPs, and study guides, all from the same source in Scholarly.
Keep exploring
More 3D model tools
3D Models (Beta)
How 3D models work in Scholarly, exports included.
3D Process Visualizer
SOPs and workflows as 3D process models.
Training Video Generator
Narrated training videos from SOPs and guides.
Scholarly Teams
Shared source libraries, roles, and one bill.
Employee Onboarding
Onboarding material built from your own docs.
PDF to 3D Model
Build a labelled 3D model of what a PDF explains.
Quiz Generator
Check understanding with a quiz from your source.
Build your first 3D explainer
Sign up, open a training PDF, and ask for a 3D model of what it explains.
Beta. A full AI build uses 1 AI Creation Credit; small chat edits are free. Exports need a paid plan.