Upload a PDF, report, spec, or set of notes and get a JSON file with a stable, self-describing schema — consistent key names, records in a top-level array, and no prose or code fences wrapping the output. Built for developers and analysts who need a document as data.
Free to start. One lifetime AI Creation Credit on the Free plan. No credit card required.
[
{
"clause_id": "4.2",
"title": "Payment terms",
"obligation": "Client pays invoices within 30 days of receipt.",
"deadline_days": 30,
"source_page": 4
},
{
"clause_id": "7.1",
"title": "Confidentiality",
"obligation": "Both parties keep disclosed information confidential for the term.",
"deadline_days": null,
"source_page": 7
}
]Schematic example. Every record uses the same keys; a null means the source did not state the value, and nothing is wrapped in prose or code fences.
The JSON Export tile inside Scholarly's AI File Creator turns your material into a single, machine-readable file.
Upload PDFs, Word docs, PowerPoints, spreadsheets, or text files, pick files from your library or Google Drive, or paste a URL. Use up to 10 sources (20 on Laureate) and choose specific PDF page ranges.
Choose the JSON Export tile. In custom instructions, name the keys you want on each record and what counts as one record — a clause, a product, a study, a glossary entry.
The .json file is saved to your library and downloads instantly. Load it in a script, import it into a database, or pass it to the next step of a pipeline.
Anything that another program, not a person, needs to read next.
Turn recurring PDF reports, invoices, or filings into records with the same keys every time, so the downstream ingestion step never has to change.
Example: monthly vendor report → array of line items with vendor, period, amount, and category keys.
Pull contract obligations, regulatory requirements, or technical specifications into one record per item with an id, title, text, and the page it came from.
Example: services agreement → obligations array with clause_id, party, obligation, deadline_days.
Convert a product catalogue, a course outline, or a glossary into the exact shape your schema expects and load it without hand-mapping fields.
Example: glossary PDF → terms array with term, definition, category, and related_terms.
Extract study metadata from papers — sample size, method, outcome measures, key findings — into records you can filter, compare, and chart programmatically.
Example: three papers → studies array with title, year, n, design, primary_outcome.
The output follows the conventions parsers and pipelines expect, so you spend no time cleaning it up.
Key names are consistent across every record and describe the data they hold, so the file reads without a separate legend.
The file is an array of records at the top level — the shape most import tools and scripts expect by default.
The output is the JSON itself: nothing before it, nothing after it, no Markdown wrapper to strip before parsing.
Values come from the files you upload. When the source does not state a value, the field is left empty rather than guessed.
Name the keys and the record boundary in custom instructions and the generator uses them, so the output matches the schema you already have.
For PDFs, select the page range the data should be built from, so only the relevant section contributes records.
Updated August 2026
Upload up to 10 sources on Premium, or 20 on Laureate (1 on the Free plan) — PDFs, Word docs, slides, spreadsheets, text files, Google Drive files, or a URL — pick the JSON Export tile, and Scholarly generates a .json file with consistent keys and records in a top-level array, saved to your library and ready to download. The Free plan includes one lifetime AI Creation Credit and one upload (8 MB; PDFs are processed up to 32 pages). Premium ($30/mo or $144/yr) allows 10 AI Creation Credits per week and Laureate ($99/mo) includes 80 AI Creation Credits per week.
Asking a chatbot for JSON usually returns a code block with an explanation above it, a caveat below it, and key names that drift from one answer to the next. Every one of those needs to be stripped or normalised before a parser will accept it. The JSON Export tile produces the file, not a message about the file.
Because the generator reads your uploaded sources, the records are drawn from your document — the clauses in your agreement, the SKUs in your catalogue, the studies in your review. Where the document is silent, the field is left empty so the gap is visible in the data rather than filled with a plausible guess.
The result is a real .json file in your Scholarly library, stored next to the source it came from. Download it into a script or pipeline, and when the source changes, generate again with the same instructions to get the same shape.
The JSON tile is deliberately narrow. These are the boundaries to plan around.
Developers and analysts use the JSON Export tile to get documents into pipelines: vendor reports into a warehouse, contract obligations into a tracker, product specs into a catalogue service, policy documents into a searchable index. Name the keys once and every document in the same family comes out in the same shape.
Teams plans add shared libraries, so the source documents, the generated JSON, and the SOPs that describe the process stay together where the whole team can reach them.
Yes. Upload the PDF, optionally pick the page range, choose the JSON Export tile, and describe the keys each record should have. You get a .json file with records in a top-level array and consistent key names.
Describe them in custom instructions before generating — for example "one record per clause with keys clause_id, title, obligation, deadline_days". The generator keeps key names consistent across every record.
No. The JSON Export tile produces the JSON itself with no prose or code fences around it, so it can be parsed directly.
Use the CSV Table tile when you need one flat table for Excel, Google Sheets, or a database import. Use JSON when records have nested or list-valued fields, or when a script or API will read the file.
Scholarly is free to start: the Free plan includes one lifetime AI Creation Credit and one upload of up to 8 MB (PDFs are processed up to 32 pages). Premium ($30/mo or $144/yr) allows 10 AI Creation Credits per week, and Laureate ($99/mo) includes 80 AI Creation Credits per week.
Keep exploring
The creator this JSON tile lives in — CSV, Markdown, calendar, and Excel files too.
Flat records for a spreadsheet or database import instead of nested JSON.
Build an Excel workbook with sheets and formulas from the same sources.
Pull PDF tables straight into a spreadsheet.
Human-readable docs for the same material.
Dated items as an importable .ics file.
Schema-consistent records extracted from your own documents.
Trying your first source? Start Free. Working with new material each week? Premium includes 10 AI Creation Credits a week. Need more capacity? Compare Laureate.
Pricing shown in USD by default. Local currency may be available in app or at checkout.
AI chat
Premium and Laureate include unlimited AI chat. GPT 5.6 Sol and Claude Opus 5 are reserved for credit-metered AI creations.
AI Creation Credits
AI Creation Credits share one balance across every creation tool. Most models use 1 credit, Sonnet and Kimi use 2, and Frontier models Sol and Opus use 3.
Podcast length
Free episodes are fixed at 2 minutes. Paid plans can set a target length up to 60 minutes.
Video lecture length
Free lectures with a length control are fixed at 2 minutes. Paid plans can set a target up to 45 minutes. Short uses its own short video format.
File uploads
PDF to flashcards
Sources per creation
Practice questions
Practice exams
Voice mode
Autocomplete
Export to Anki
Support
Scholarly has enhanced the quality of notes and questions I administer to my tutees. Insightful, to the point.
TD Georgas
Tutor
I have very good experience with Scholarly it summarize me scientific text in hovel academic level with citation. I use this for any therapeutic area . It is great and useful tool.
Diana
Scholarly user
Scholarly has been a valuable tool for my studies. The AI-generated flashcards and intuitive features make organizing and retaining information much easier.
Briana
Scholarly user
This app is great for studying for big test. Drop your PDF's in the system and it'll do the trick. You can organize it specifically for your needs.
Kelvin
Scholarly user
Yes! The free plan includes core study tools with lifetime allowances: 3 AI Chat messages, 500 autocomplete words, 5 quiz questions, 15 voice minutes, 1 practice exam, one free AI Creation Credit total, and 1 file upload. These allowances do not reset. Upgrade to Premium for 10 AI Creation Credits per week and unlimited uploads.
AI Creation Credits are shared across flashcards, podcasts, videos, slides, AI Documents, Deep Research, and the Transcribe tool. The selected model determines the credit cost. Recording live audio and saving its transcript uses your file upload allowance instead; it does not use AI Creation Credits.
Absolutely. There are no contracts or commitments. You can cancel your subscription at any time from your account settings, and you'll keep access until the end of your billing period.
We accept all major credit and debit cards through Stripe. Pricing is displayed in USD by default, but local currency is available in the app.
Yes. For a school or organization-wide rollout, contact us at hello@scholarly.so and we'll help you find the right setup.
You'll see a prompt to upgrade. Your existing work is never lost — limits only apply to new actions. Free-plan allowances are lifetime credits and do not reset. Premium includes 10 AI Creation Credits per week, podcasts up to 60 minutes, video lectures up to 45 minutes, unlimited uploads, chat, autocomplete, quizzes, and exams, plus more daily voice time.