• Skip to main content
  • Skip to secondary menu
  • Skip to primary sidebar

FromThePage Blog

Crowdsourcing, transcription and indexing for libraries and archives

  • Home
  • Interviews
  • crowdsourcing
  • how-to
  • Back to FromThePage
  • Collections

Introducing Gemini 3.0 Support in FromThePage

November 22, 2025 by FromThePage Leave a Comment

When Ben sent me Mark Humphries’ report on testing a new, unreleased Gemini model, I got scared. And excited.

Mark is a historian and digital humanist who’s gone deep on analyzing AI tools for textual transcription. He understands the dangers of “seductive plausibility” in LLM outputs. He knows what researchers and historians need from archival text. He measures errors against human-transcribed “ground truth” in his experiments; not relying on “spot checking” or intuition. So I tend to believe him when he says:

...LLMs are getting good enough to be trusted in the way we might trust knowledgeable, trained humans on similar knowledge-work tasks. If true, that has enormous implications for what I do as a historian and how humanity relates to information.”

At the same time, we know a lot of you are experimenting with AI and HTR – we’re getting more requests for AI Assist using Transkribus now than we did a year ago when we released it. And you are using tools built for businesses or consumers – ones that make archivists and librarians work around their systems, rather than within them. (Do you really want to copy and paste text from ChatGPT?)

So we built it. In a 3-day sprint of thinking and coding and testing, we added Gemini integration to FromThePage. First, with Gemini-2.5-Pro, which was merely “good”, rather than the “very good” we anticipated from Gemini 3. When Gemini 3 came out Tuesday, we just swapped out the model and were good to go.

We resisted LLM transcription for a long time because we couldn’t easily get the bounding boxes for our beloved AI Assist overlay – text on the image – and this Gemini integration doesn’t have that. It does have “AI Draft”, a button that copies the AI text into the editor, and a new “AI” tab that shows you the AI generated text.

So… are you intrigued? Scared? (I am!)

But I’m heartened by what one of our initial testers, Sarah A. Hanson-Pareek, the Program Director at the Digital Imaging Lab, Digital Library and Photographs at the University of South Dakota said:

The transcriptions turned out like I’d expected! Gemini is remarkable and technology is changing by years every day...Thank you SO MUCH for doing this. It makes all the world to those of us with very small staff. I have been wanting to work with Gemini and HTR for months, but simply do not have enough of me to go around. Also, Gemini integrated with your product makes the world a happy place.😊”

I’d encourage you to try your own experiment – start a 200 page trial by uploading a zip file of images or PDFs (or importing a IIIF manifest) and checking the “generate AI Drafts with Gemini” box. And please, let us know what you discover!

Not ready to experiment yet? We’re hosting a webinar on December 11th where we’ll dive deeper into this integration and what we’ve learned. Sign up here.

Filed Under: ai & crowdsourcing, Uncategorized

Reader Interactions

Leave a Reply Cancel reply

You must be logged in to post a comment.

Primary Sidebar

What’s Trending on The FromThePage Blog

  • Introducing Gemini 3.0 Support in FromThePage
  • Classifying the Mistakes We Make When We Transcribe
  • How to Handle Racial or Ethnic Slurs &…
  • Is That Transcription Really Human?
  • How Do I Read Old Handwriting?
  • Guide to Digitizing Your Archives

Recent Client Interviews

An Interview with Candice Cloud of Stephen F. Austin State University

An Interview with Shanna Raines of the Greenville County Library System

An Interview with Jodi Hoover of Digital Maryland

An Interview with Michael Lapides of the New Bedford Whaling Museum

An Interview with NC State University Libraries

Read More

ai artificial intelligence crowdsourcing features fromthepage projects handwriting history iiif indexing Indianapolis Indianapolis Children's Museum interview Jennifer Noffze machine learning metadata newsletter ocr paleography podcast racism Ryan White spreadsheet transcription transcription transcription software

Copyright © 2025 · Magazine Pro on Genesis Framework · WordPress · Log in

Want more content like this?  We publish a newsletter with interesting thought pieces on transcripion and AI for archives once a month.


By signing up, you agree to our Privacy Policy and Terms of Service. We may send you occasional newsletters and promotional emails about our products and services. You can opt-out at any time.  We never sell your information.