Select two exports and review their references with explicit field mappings.
400,000 bytes/file · 100,000 UTF-16 units · 500 data rows/file
Compare selected exportsAdvanced tools
Enhance images, trace SVG paths, reuse PDF content, search English documents, create subtitles, edit PDFs.
Free to use, without an account. Your files are processed in your browser. Some tools download an engine or model on first use.
Build a directed flow or architecture diagram from named boxes and connections.
Use 1–100 boxes. Use at most 200 connections.
Generate diagram
Make static GLB models lighter. Compare the original and the optimized model before downloading.
One GLB · 25 MiB · Static models only
Optimize model
Enlarge a small photo or illustration with the compact Real-ESRGAN super-resolution model, locally.
PNG / JPG / WebP · One file · 10 MiB per file · 1024 px per side · 1,000,000 pixels · 2× / 4× PNG output. First-use model download, plus engine: 4.72 MiB.
Process
Paint over a small distraction and let MI-GAN estimate the image underneath.
PNG / JPG / WebP · One file · 10 MiB per file · 2048 px per side · 4,000,000 pixels · PNG output. First-use model download, plus engine: 26.78 MiB.
Process
Trace a raster logo or drawing into actual SVG paths with VTracer.
PNG / JPG / WebP · One file · 10 MiB per file · 1024 px per side · 1,000,000 pixels · SVG output ≤ 5 MiB.
Process
Extract printed text from images or scanned PDF pages, correct the result, and download a TXT file.
Up to 10 images (50 MiB total) or one PDF with 20 pages; 20 MiB per file. Tables and handwriting need manual review; no searchable-PDF export.
Extract text
Replace supported PDF text, add annotations, fill supported forms, and export a PDF copy.
One PDF: up to 20 MiB and 200 pages. Scanned text is not directly editable; replacement fonts can differ.
Edit a PDF
Convert a selectable-text PDF into Markdown with the local PDF Inspector WASM engine.
PDF · One file · 20 MiB per file · 1–100 PDF pages. Text PDFs; no OCR.
Process
Find relevant passages in English PDF, TXT or Markdown files using a local MiniLM embedding model.
PDF / TXT / MD · up to 10 files · 5 MiB per file · Total 20 MiB · 1–100 PDF pages · 200 passages · 250,000 extracted characters. First-use model download, plus engine: 22.59 MiB. English documents and English questions; no generated answers. TXT and Markdown must use UTF-8. Passages are split to fit the local model. Dense technical text may reach the 200-passage limit sooner; split the files if needed. Questions must also fit the model: shorten a rejected question and retry without rebuilding the index.
Process
Recognize English speech locally, review the text and timing, and export SRT or VTT subtitles.
Recognition currently supports English. Timings are estimated. Media: up to 100 MiB and 10 minutes.
Create subtitles
Rotate a real 3D body model, find a structure, and isolate or separate its body systems.
Requires WebGL 2 and a model download. Simplified educational geometry; not for medical decisions.
Explore the model
Extract text-based PDF tables to CSV or JSON. Compare cells with the original before downloading.
One PDF · 20 MiB · Up to 20 pages
Choose PDF
Describe a scene in a short MP4, rank sampled visual frames, inspect the original, and download a compact JSON report.
One MP4; 50,000,000 bytes; parsed duration at most 120 seconds, also subject to the chosen 20-sample limit. · WebGPU
Find momentsWhich tool should I choose?
Use text extraction for scanned pages and images; use PDF Editor to change supported text in a PDF. Subtitle Studio starts from an English recording or an existing subtitle file. Check each tool's limits before loading a large file, then review the exported result.