trueparse
Open Beta

Turn PDFs into data you need.

Drop a PDF, define what you need, and let AI do the rest. Your data comes back clean and organized — delivered straight to your inbox, Slack, webhooks, or wherever you need it.

Free to startREST APIGoogle Drive sync5+ delivery targets
TrueParse extraction results — invoice data extracted into structured columns

How it works

From PDF to structured data in four steps.

STEP 01

Define your structure

Choose the fields you want to extract — vendor name, invoice number, total amount, due date, line items, and more.

STEP 02

Upload your PDF

Use the playground to test instantly, connect a Google Drive folder, or send documents via the REST API.

STEP 03

AI extracts your data

TrueParse maps every field to your typed schema — predictable outputs, consistent null handling, no guesswork.

STEP 04

Deliver anywhere

Results flow automatically to webhooks, Amazon S3, Slack, or email. Get JSON for your API or Excel for your team.

Built for everyone

Whether you prefer code or clicks, TrueParse fits your workflow.

For Developers

REST API with full control. Integrate into any stack.

  • Single API endpoint
  • Typed JSON responses
  • Async processing with webhooks
  • Batch processing via API
Quickstart Guide

No-Code

Connect Google Drive, get Excel. Zero code required.

  • Connect in 30 seconds
  • Batch process entire folders
  • Get results as Excel
  • Auto-delivery to email or Slack
Connect Google Drive

Why TrueParse

Schema-First Extraction

Define your output schema once. Every extraction conforms to your types with consistent null handling — no regex, no guesswork.

Production-Ready API

Clean REST API with typed responses. Single endpoint, async processing, webhooks, and event-driven callbacks built in.

Google Drive Sync

Connect a Google Drive folder and get structured data back automatically. Batch process entire folders with zero code.

Deliver Results Anywhere

Configure per-schema delivery. Results flow to webhooks, Amazon S3, Slack, or email — automatically.

trueparse
Open Beta

Ready to extract data from your PDFs?

Start free — no credit card required. See results in under a minute. Tell us what documents you process and we'll show you what TrueParse can do.

Get in touch

Tell us what documents you process. We'll reach out within 24 hours.

One API call. Structured data back.

Send a PDF with your schema ID. Get typed JSON back — or download as Excel. Async processing with webhook callbacks for production workflows.

# Send a PDF
curl -X POST https://api.trueparse.ai/v1/jobs \
-H "Authorization: Bearer $TRUEPARSE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"pdf": "[base64]", "schema_id": "sch_abc123"}'
# Response: 202 Accepted
{ "success": true,
"data": { "job_id": "job_xyz789", "status": "pending" } }

Built for document-heavy workflows

TrueParse handles the documents your team processes every day.

HR Teams

Process 50+ offer letters and resumes weekly

Sync HR folder, get candidate data in Excel automatically

Offer letters, Resumes, Employment contracts

Finance

Reconcile hundreds of vendor invoices monthly

Drop invoices in shared folder, get structured line items

Invoices, Receipts, Purchase orders

Engineering

Automate contract parsing for compliance checks

Call the API from your CI pipeline, get typed JSON back

Contracts, SOWs, NDAs

Operations

Extract shipping details from carrier documents

Upload BOLs to shared folder, deliver data to your TMS

Bills of lading, Shipping manifests, Customs forms

Start extracting data from your PDFs today.