Turn Any PDF into a Clean Google Doc with Mistral OCR

Description

Upload a PDF and instantly get a neatly formatted Google Doc with all the readable text—no manual copy-paste, no messy line breaks.

What this workflow does

Accepts PDF uploads via a public form
Sends the file to Mistral Cloud for high-accuracy OCR
Detects and merges page images with their extracted text
Cleans headers, footers, broken lines, and noise
Creates a new Google Doc in your chosen Drive folder
Writes the polished markdown text into the document

What you need

Mistral Cloud API key with OCR access
Google Docs & Drive credentials connected in n8n
Drive folder ID for new documents
A PDF file to process (up to 100 MB)

Setup

Import the workflow into n8n and activate credentials.
In Trigger • Form Submission, copy the webhook URL and share it or embed it.
In Create • Google Doc, replace the default folder ID with yours.
Fill out Mistral API key under Mistral Cloud API credentials.
Save and activate the workflow.
Visit the form, upload a PDF, name your future doc, and submit.
Open Drive to view your newly generated, clean Google Doc.

Example use cases

Convert annual reports into editable text for analysis.
Extract readable content from scan-only invoices for bookkeeping.
Turn magazine PDFs into draft blog posts.
Digitize lecture handouts for quick search and annotation.
Convert image-heavy landing pages / advertorials into editable text for AI to analyze structure and content.