Resume parsing

Every resume.Instantly searchable.

Skills, work history, education, contact — extracted from PDFs, Word docs, scans, and even LinkedIn screenshots. Bias-aware fields off by default.

Start extracting See the API

100 pages free No card SOC 2 in progress

app.docparse.io / extractions / sarah-chen-resume.pdf

Live

Sarah Chen

Senior Product Designer · 8 yrs

Emailsarah.chen@hey.com

LocationBerlin, DE

LatestLead Designer, Figma

Years exp8

Top skillDesign systems

EducationRISD, BFA, 2017

JSONCSVWebhook98.6% confidence

{
  "name": "Sarah Chen",
  "email": "sarah.chen@hey.com",
  "location": "Berlin, DE",
  "years_exp": 8,
  "latest_role": "Lead Designer, Figma",
  "skills": ["Design systems","Figma","Prototyping"],
  "education": [{...}]
}

Extracted in 2.4s · 7 fields

Scroll

Pipe extracted data into any of these — via Zapier or signed webhooks

Zapier

Google Drive

Gmail

Slack

Sheets

Notion

Airtable

Webhook

Zapier

Google Drive

Gmail

Slack

Sheets

Notion

Airtable

Webhook

Why DocParse

Three reasons teams switch to us

Bias-aware by default

Photos, names, ages, and graduation years are filtered out unless you explicitly opt in. Configurable per region and role.

EEOCcompliant out of the box

Works on every format

PDF, DOCX, RTF, scans, screenshots from LinkedIn, even paste-from-email. We rebuild the layout before extraction.

8 fmtsincluding LinkedIn screenshots

Skills that mean the same

Normalizes "JS", "JavaScript", and "ES6" into one canonical skill. Maps to ESCO and your own taxonomy.

34kskills in the canonical graph

How it works

From raw resumes
to structured data, in four steps.

Drop document, paste URL, or POST file

PDFPNGJPGTIFFDOCXHEICHTMLEMLXLSX

The schema

Starter schema for resumes.
Tweakable in seconds.

The resumes template comes with a 10-field starter schema based on the most common fields teams pull from resumes. Add your own fields, mark which are required, and change types in the dashboard or via the REST API.

Resumes · default schema

namestringrequired99.7%

emailstringrequired99.5%

phonestringoptional98.9%

locationstringoptional97.8%

years_expintegerrequired96.4%

skillsarrayrequired98.1%

work_historyarrayrequired97.6%

educationarrayoptional98.2%

languagesarrayoptional99.0%

certificationsarrayoptional97.4%

JSON SchemaTypeScriptPython

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Resumes",
  "type": "object",
  "required": [
    "name",
    "email",
    "years_exp",
    "skills",
    "work_history"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "phone": {
      "type": "string"
    },
    "location": {
      "type": "string"
    },
    "years_exp": {
      "type": "integer"
    },
    "skills": {
      "type": "array"
    },
    "work_history": {
      "type": "array"
    },
    "education": {
      "type": "array"
    },
    "languages": {
      "type": "array"
    },
    "certifications": {
      "type": "array"
    }
  }
}

What to expect

Field-level accuracy per field.

Multi-modal models do the reading, and accuracy depends on document quality. The numbers below are illustrative ranges we've seen on resumes — run your own documents and compare against a small ground-truth set before you scale.

97.8%

illustrative field-level
accuracy ceiling

10starter fields

Anylanguage supported

25 MBmax file size

FieldAccuracy

name

99.7%

99.5%

years_exp

96.4%

skills

98.1%

work_history

97.6%

education

98.2%

phone

98.9%

location

97.8%

The API

One endpoint.
Every output you need.

# Extract with one POST
curl -X POST "https://api.docparse.io/v1/resumes" \
  -H "Authorization: Bearer $DOCPARSE_KEY" \
  -F file=@"sarah-chen-resume.pdf" \
  -F schema="resume" \
  -F webhook="https://api.acme.co/incoming"

# Returns:
{
  "status": "complete",
  "confidence": 0.987,
  "latency_ms": 2412,
  "data": { ... }
}

Plain HTTP, no SDK lock-in

Bearer-token auth with revocable, SHA-256-hashed API keys. Call it from any language that can hit a REST endpoint — we publish docs and copy-pasteable snippets, not opinionated wrappers.

cURLPythonNode.jsGoRubyPHPJava.NET

Signed webhooks for async

Register an endpoint, set the events, and we POST signed deliveries (HMAC-SHA256, Standard Webhooks spec) as extractions finish. Every attempt is logged in the dashboard with response code, body, and timing.

Webhook delivery log · per-endpoint retries

The alternatives

Why teams switch from regex.

A look at how DocParse compares to the three things you've probably already tried.

Regex + scripts

Manual review (BPO)

Sovren / RChilli

DocParse

Works on a layout it has never seen

partial

Handles handwriting and scans

partial

Custom fields without per-vendor setup

Multi-lingual out of the box

partial

REST API + signed webhooks + Zapier

partial

Pricing scales with pages, not seats

partial

Free tier, every month, forever

partial

Time-to-first-extraction

Days

Weeks

5 minutes

Where the data goes

Reach the tools you already run.

DocParse ships two integration surfaces directly — REST API and signed webhooks — plus a native Zapier app that opens up everything else.

Zapier

Automation

Webhooks

API

REST API

API

JSON export

Export

CSV export

Export

Google Drive

via Zapier

Google Sheets

via Zapier

Gmail

via Zapier

Outlook

via Zapier

Slack

via Zapier

Dropbox

via Zapier

Airtable

via Zapier

Notion

via Zapier

HubSpot

via Zapier

Salesforce

via Zapier

Make.com

via Webhooks

n8n

via Webhooks

Postgres

via Webhooks

REST API · Signed webhooks (HMAC-SHA256) · Zapier to 6,000+ apps · JSON / CSV export

Common patterns

How teams use DocParse for resumes.

Illustrative scenarios drawn from teams piloting DocParse — names and figures are examples, not customer quotes.

“

Sovren was 89% accurate on skills. DocParse hit 98% on day one and the bias-aware defaults saved us a Q3 of legal review.

Jordan Yi

VP Talent · Halcyon

+9ptsskill-match accuracy

“

Our ATS could only ingest cleanly-formatted PDFs. DocParse means recruiters can drop a Word doc, screenshot, or LinkedIn paste — all roads lead to JSON.

Tomás Reyes

Head of Talent Ops · Northwave

8 formatsall parsed cleanly

“

We process 12,000 resumes a week. Latency dropped from 18s to 1.4s and we cut our infra bill by half. Same team, four times the throughput.

Sun Park

Engineering Manager · Quartile

4×throughput at half cost

Frequently asked

The questions teams ask before they sign up.

How is bias handled?

Photos, full names, ages, addresses, and graduation years are stripped by default. Each can be enabled per-jurisdiction with a documented audit trail.

Can it parse non-English resumes?

60 languages including Arabic, Hebrew, Mandarin, Japanese, and Korean. Skill normalization works across languages — "JavaScript" and "JavaScript" map to the same canonical token.

Do you map skills to a taxonomy?

ESCO, O*NET, and a custom taxonomy you upload. Each skill is returned with the source phrase, normalized canonical form, and taxonomy ID.

What about scans?

OCR is built in. Hand-annotated resumes (a manager scribbled comments) parse cleanly with the comments captured separately.

Does it integrate with my ATS?

Greenhouse, Ashby, Lever, Workday, SmartRecruiters, and a generic webhook. Most customers wire it as a pre-processor before the ATS ingests.

Parse every resume in every format.

Bias-aware by default, 60 languages, ATS-ready output. Free for the first 100 resumes.

Start extracting Talk to sales

Free for first 100 pages 5-minute setup No credit card

Every resume.Instantly searchable.

Three reasons teams switch to us

Bias-aware by default

Works on every format

Skills that mean the same

From raw resumes
to structured data, in four steps.

Define the fields

Upload the file

Multi-modal AI reads it

Get structured data back

Starter schema for resumes.
Tweakable in seconds.

Field-level accuracy per field.

One endpoint.
Every output you need.

Plain HTTP, no SDK lock-in

Signed webhooks for async

Why teams switch from regex.

Reach the tools you already run.

How teams use DocParse for resumes.

The questions teams ask before they sign up.

Parse every resume in every format.

Every resume.Instantly searchable.

Three reasons teams switch to us

Bias-aware by default

Works on every format

Skills that mean the same

From raw resumesto structured data, in four steps.

Define the fields

Upload the file

Multi-modal AI reads it

Get structured data back

Starter schema for resumes.Tweakable in seconds.

Field-level accuracy per field.

One endpoint.Every output you need.

Plain HTTP, no SDK lock-in

Signed webhooks for async

Why teams switch from regex.

Reach the tools you already run.

How teams use DocParse for resumes.

The questions teams ask before they sign up.

Parse every resume in every format.

From raw resumes
to structured data, in four steps.

Starter schema for resumes.
Tweakable in seconds.

One endpoint.
Every output you need.