Turn resumes and CVs into structured JSON. Contact details, the full work history, education, skills, and certifications come back typed and ready for your ATS or candidate database. Every resume has a different layout - the schema does not care.
Send the resume and a schema. Every role and every degree comes back as its own object, in order, with dates you can actually sort on.
curl -X POST \
https://api-parse.conversiontools.io/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@resume.pdf" \
-F 'schema={
"name": "string",
"email": "string",
"phone": "string",
"location": "string",
"summary": "string",
"work_experience": [{
"company": "string",
"title": "string",
"start_date": "string",
"end_date": "string",
"description": "string"
}],
"education": [{
"institution": "string",
"degree": "string",
"field": "string",
"graduation_year": "number"
}],
"skills": ["string"],
"certifications": ["string"],
"languages": ["string"]
}'{
"status": "completed",
"pages": 2,
"data": {
"name": "Mara Velichko",
"email": "mara.velichko@example.com",
"phone": "+1 415 555 0182",
"location": "Oakland, CA",
"summary": "Supply chain analyst, eight years in high-volume distribution.",
"work_experience": [
{
"company": "Fernbrook Logistics",
"title": "Senior Supply Chain Analyst",
"start_date": "2022-03",
"end_date": "present",
"description": "Owned demand forecasting for the northern network."
},
{
"company": "Talloak Retail Group",
"title": "Inventory Analyst",
"start_date": "2018-06",
"end_date": "2022-02",
"description": "Ran replenishment planning across 40 stores."
}
],
"education": [
{
"institution": "Redmont State University",
"degree": "BSc",
"field": "Operations Management",
"graduation_year": 2018
}
],
"skills": ["Demand forecasting", "Inventory planning", "S&OP"],
"certifications": ["Lean Six Sigma Green Belt"],
"languages": ["English", "Ukrainian"]
}
}No two resumes share a layout. A schema describes what you want, not where it sits on the page.
Two-column designs, tables, hybrid layouts, and plain text all go through the same schema. When a new format shows up there is nothing to configure.
Each position comes back with company, title, and start and end dates as separate fields, so tenure and employment gaps become computable instead of being buried in a paragraph.
Candidates send phone photos and scanned PDFs as often as clean exports. OCR is applied automatically, so both land in the same pipeline.
Yes. The text is read in whatever language it was written in, while your schema field names stay in English. A candidate record built from a German or Spanish CV lands in exactly the same shape as one built from an English CV.
Extraction is driven by meaning rather than by headings, so a CV that lists positions without an "Experience" title still produces a work_experience array. Fields that genuinely are not on the page come back empty.
Yes. Declare each one as an array of strings and you get clean lists you can index for search, instead of a single comma-heavy line of text.
Extraction is asynchronous: submit each file, then poll for the result or register a webhook to be called when it finishes. Saved schemas let you define the fields once and reuse them for every candidate.
Uploaded documents are deleted automatically within 24 hours. Extracted data is encrypted in transit and at rest and is never used to train models.
The same schema-driven API works across every document type. Define a schema once, extract from thousands of files.
Extract structured JSON from any document with custom schemas.
Parse any PDF into structured JSON, scanned or digital.
Vendor, line items, totals, tax, and dates from invoices.
Store, items, totals, and payment method from receipts.
PO number, vendor, buyer, and SKU-level line items.
Transactions, running balances, and dates for reconciliation.
Box-level data from W-2, 1099, and other tax forms.
Parties, dates, governing law, and key clauses.
Carrier, parties, ports, containers, and cargo.
Credit amounts matched back to the original invoice.
Payments split across invoices for cash application.
Meter readings, charges, and totals from any provider.
Line items and periods from balance sheets and reports.
Vendor quotes in one shape so you can compare them.
Earnings, deductions, taxes, and year-to-date totals.
Fields and MRZ from passports and ID cards.
Rent, term, deposits, and renewal deadlines.
Claim and policy numbers, dates, and claimed amounts.
Packages and SKU-level lines for receiving.
Ordered versus delivered quantities and sign-off.
Free tier covers your first 100 pages a month. No credit card to start.