Skip to main content
Submit a document for OCR. We extract text, detect tables, and optionally generate a searchable PDF. Processing is async — you get a job ID immediately, then poll for results or use webhooks.
Endpoint
Response

Parameters

Required

Optional

OCR engines

For legal documents: Start with doctr. If you’re getting poor results on forms or tables, try paddleocr.

Features

Enable additional processing:
JSON

Checking status

Poll the job to check if processing is complete:

Using webhooks

For large documents, use webhooks instead of polling:
We POST the completed job to your callback URL when processing finishes.

Vault objects (s3://)

If the document is already in one of your vaults, pass its s3:// path: the vault’s filesBucket followed by the object’s s3Key. The API key must have read access to that vault and object. Any other s3:// path returns 404.
We generate a short-lived presigned URL for the OCR service. For files in your own S3 bucket, presign them yourself and pass the HTTPS URL.

Examples

Scanned deposition

Medical records with tables

Handwritten notes