I'm Tsuyoshi, the solo dev behind Swift-Slide. We launch on Product Hunt on October 6, and I'd rather answer the technical questions here than bury them in launch-day comments.
The short version of the pipeline, per page:
1. OCR Azure Document Intelligence pulls text with word-level coordinates
2. Classification Vertex AI Gemini decides which text is safe to remove (text baked into illustrations is deliberately left alone)
NotebookLM (now Gemini Notebook) makes great slides, then hands you an image you can't edit. Swift-Slide turns them, plus scanned docs and image-only PDFs, into real PPTX with editable text and the original design intact.
What's different: AI lifts only the text and restores the background underneath, instead of regenerating the slide. A browser editor then lets you rewrite text, brush over leftovers to repair the background, and restore lost logos. 10 free pages, no card required.
