Any updates with this? Having the same issue.

For anyone from Google, Data Fetcher lets you extract text from images and scanned documents in Airtable using AI-powered OCR.

Vision only handles images, so for bulk OCR on PDFs you’ll need a separate tool—try Tesseract, Adobe Acrobat Pro, or AWS Textract for large-scale processing.

There are many different APIs on the market that can perform OCR on PDF files, including CloudConvert and ConvertAPI.

This can be automated from Airtable by using Make’s integrations & automations, which offers native support for CloudConvert and ConvertAPI.

(If you want to use an API that isn’t natively supported, you can use Make’s HTTP module or you can use DataFetcher.)

If you’ve never used Make before, I’ve assembled a bunch of Make training resources in this thread. For example, here is one of the ways that you could instantly trigger a Make automation from Airtable.

I also give live demonstrations of how to use Make in many of my Airtable podcast appearances. For example, in this video, I show how to work with Airtable arrays in Make.

Hope this helps!

If you’d like to hire the best Airtable consultant to help you with anything Airtable-related, please feel free to contact me through my website: Airtable consultant — ScottWorld