Drop a script here, or click to browse
Supports PDF, DOCX, PNG, JPG, WebP
How it works
- PDFs: If the PDF has a text layer, we extract it directly — perfect accuracy, no OCR needed. If it's a scanned PDF, we render each page and OCR it.
- DOCX: Read directly from the file structure. 100% accurate.
- Images: Preprocessed (grayscale → adaptive threshold → upscale) before OCR for best results.
- Flagging: Low-confidence words are highlighted in yellow so you can review and fix them before use.
- Script parsing: Detects character names and strips noise like page numbers. Stage directions in parentheses can be stripped from slides.
- Export: Configure slide size, font, and line limits, then export to PowerPoint or Google Slides.