Everything in the catalog

Extract text from an image and translate between English and Chinese.

Phoneme-level feedback on English pronunciation.

Detailed planner page for a Seoul and Tokyo trip.

Personality adjectives with audio and Spanish translations.

Flashcards for transport words in English, Russian and Kazakh.

Generates vacation ideas from the preferences you enter.

English vocabulary quiz with instant scoring.

Interactive games for practising English vocabulary.

Trip planner that checks the weather for your destination.

Reads a single line of text from a cropped photo using TrOCR.

Generates a 3D asset from an input image using the TRELLIS.2 model from Microsoft.

Extracts text from Arabic images or PDFs into Markdown.

Click an object, then remove it or fill it with new content using segmentation and inpainting.

Runs an agent loop in the browser tab on top of a ternary Bonsai 2 model using WebGPU.

Generates Arabic poetry from a short prompt.

Identify which language a text is in and spot mixed-language switching.

Translates sentences into emoji and emoji back into words.

Upscales pictures with a super-resolution model.

Adds diacritics (tashkeel) to Arabic text.

Vector search over documents using a Postgres running in WebAssembly (PGlite) inside the browser.

Detects objects in a video stream frame by frame with a model running on WebGPU.

Video generation with a synchronized soundtrack

Runs a small coding agent entirely in the browser using WebGPU, with no server needed for the model.

Segments characters out of anime pictures.