PowerPoint to Text in the browser is not a generate

/free-tools/pptx-to-text never spends a credit. Do not pay a model to do an in-browser file job. PowerPoint to Text pulls slide copy and speaker notes from a .pptx on your own machine. Nothing is uploaded. No account. No model. That is a different surface from generation, which always costs credits on Versely.

The free tools rule is the product constraint: nothing on that shelf calls a model, an API, or the network. Work runs in the browser (Canvas, File API, ZIP). Versely has no free tier for generation — every generate spends credits — so a "free tool" that quietly billed would be a lie. This tool is free because it is free to run.

A .pptx is a ZIP, not a prompt

A .pptx is an Open Packaging Convention archive: a ZIP of XML parts. Slide text lives in ppt/slides/slideN.xml. Speaker notes live in ppt/notesSlides/notesSlideN.xml. The extractor reads those parts, joins <a:t> runs, and keeps paragraph breaks so a title does not weld onto the first bullet.

That is why it can read a .pptx and cannot read a .ppt. The older .ppt is a proprietary binary. It is not a ZIP. Re-save as .pptx from PowerPoint or Keynote. Password-protected or corrupt archives fail for the same reason: they are not a readable ZIP of those parts.

It does not OCR. Words that are pixels — a screenshot, a chart exported as an image, a logo — are not text runs. They will not appear. If the deck's argument is locked inside pictures, this tool will not hallucinate it back. That is honesty, not a missing feature. Paying a vision model to "read the slides" is a generate. You would be buying transcription of pixels, on the credit meter, for a job the XML already finished for real text.

Speaker notes are usually the closest thing a deck already contains to a narration script. Include them when you extract. That is the fastest route from a presentation to a voiceover script. The voiceover itself is a later, billed job.

Credits belong to a different surface

What it costs is credits, with a formula per job type: per second, per 1,000 characters, per megapixel, per export. TTS is characters. Video is usually seconds. Editor exports are priced as exports. None of those meters apply to unzipping XML in the tab.

Do not:

• Upload the deck to a video model and prompt "narrate these slides." That is a generate, and it will not honour speaker notes as a text layer.
• Run a paid "PPT to script" SaaS that ships the file to a server for the same unzip this page does locally.
• Treat PowerPoint to Text as a slide renderer. Rendering DrawingML — themes, masters, fonts — is not this tool. Faking a slide image would look like the deck without being the deck. The UI declines that instead of pretending.

If you needed the embedded pictures and clips at original resolution, that is the sibling PowerPoint Media Extractor — still in-browser, still zero credits, still not a generate. Scaling on the slide does not shrink the stored file. This text tool does not replace that extractor, and the extractor does not replace this text tool.

When the script exists, then open a billed row: TTS, a talking model, captions. Quote the credit cost before you confirm, which the app always does. The extract was free. The generate is not. Mixing them in your head is how a zero-credit job becomes a surprise invoice.

FAQ

Does PowerPoint to Text use any credits?

No. It never spends a credit. The work is local. Generation on Versely always spends credits; this is not generation.

Why not a .ppt?

Different format that shares a name. .pptx is a ZIP of XML. .ppt is a binary. Re-save as .pptx.

Are words in slide images included?

No. Only real text runs. Pixels need OCR, which would be a model, which would be a generate. This tool does not do that.

Can I use the extracted notes as a voiceover without paying?

The text is yours and the extract is free. Turning that text into speech is TTS or a talking generate, billed in credits. Plan it on /cost. Do not expect the extractor to speak.