Make slides from screenshots

Attached images are read, not placed

When you attach a PNG or JPG at generate time it goes through optical character recognition and what comes back is text. That text joins your prompt as source material. The image file itself never lands on a slide from this path. It is worth stating plainly because the reasonable expectation is the opposite, and the mismatch is the single most common surprise here.

Which makes it good for one specific thing

Turning interface labels into a walkthrough. A screenshot of a settings page contains the exact field names, button labels and menu items, and having those read out gives you a deck that uses the product's real vocabulary instead of an approximation. The same applies to a photographed slide from someone else's deck, a printed agenda or a whiteboard.

Putting the picture on the slide

That happens in the builder afterwards, in the image panel on any slide with a picture box. Upload takes JPEG, PNG, WebP and GIF, the picture fills its box, and the corner radius, the frame width and a drop shadow are all set from the same panel. Every image you add stays available to reuse on other slides in the deck.

OCR accuracy, honestly

Interface text at normal resolution reads well. Small print, low contrast dark mode captures, dense tables and anything at a photographed angle read less well. Numbers are where a misread does damage, since a wrong digit in a figure looks exactly as confident as a right one. Check every number a screenshot contributed before you present the deck.

A better source than a screenshot, when you have one

If the same content exists as a PDF or as text you can copy, use that instead. A text layer is read exactly rather than guessed. Screenshots earn their place when the thing you need only exists on screen, which for product walkthroughs and dashboards is genuinely often.

How it works, in three steps

1. Step 1

   Attach the screenshots

   Up to five files at 25 MB each, in PNG, JPG, WebP or GIF. This needs a Starter plan.

2. Step 2

   Say what each screen is for

   OCR gives labels, not intent. One line per screen naming the task turns labels into a walkthrough.

3. Step 3

   Add the pictures in the builder

   Open a slide's image panel, upload the screenshot, then set its corners, frame and shadow.

The full walkthrough with screenshots is in the guide Add and generate images in slides.

Limits worth knowing

• Attached images are read for text only. They are never placed on a slide by the generator.
• Attachments are a Starter feature, five files at 25 MB each.
• OCR is a guess, not a read. Verify every figure a screenshot supplied.
• Image uploads in the builder accept JPEG, PNG, WebP and GIF.

See it on a finished piece

Training and onboarding presentation

9 slides

Product launch presentation

8 slides

Conference talk deck

9 slides

Questions people ask

Related pages