siva-sub

High-performance client-side OCR with ONNX Runtime, RapidOCR and PPU PaddleOCR integration. 100+ language support. Process text from images entirely in the browser with state-of-the-art accuracy and complete privacy.

Context-aware graphics API for Remotion - fetch illustrations, icons, and doodles from 5 free sources. No API keys required.

Multi-engine browser OCR with visual results. Choose between fast mobile models (PPU) or accurate server models (OnnxOCR). Features Tesseract fallback, visual bounding boxes, 100% client-side processing, PWA support, and intelligent model caching.