Everything in the catalog

WebAssembly build of whisper.cpp that transcribes microphone or file audio inside the browser.

Demo of JavaScript OCR that reads text from images in many languages.

Web version of the Chatbox client for chatting with models from several providers using your own keys.

Chat with an AI to generate and edit draw.io diagrams such as AWS architectures and flowcharts.

Upscales and denoises anime-style art, and photos, with convolutional neural networks.

Turns any public GitHub repository into an interactive architecture diagram.

Open-source machine translation web UI and API; the hosted API needs a key but the page translates text.

Demo of a Notion-style editor that offers AI autocompletion as you write.

Grammar, spelling and style checker for dozens of languages, usable in the browser without installing anything.

Browser front end for story writing and chat that can use the AI Horde, KoboldCpp or other API backends.

Runs a small GPT-2 model in the page and shows attention and token probabilities as it generates text.

Browser chat interface for the OpenAI API with prompt library, folders and local history; bring your own key.

Describe an app idea and an open model generates a runnable code project with a preview.

Removes unwanted objects from a photo and upscales images using models that run in the browser.

Converts a recording of an instrument or voice into MIDI notes, processing audio in the browser.

Draw a user interface on a canvas and a vision model turns it into working HTML; uses your own API key.

Stable Diffusion that runs completely in the browser through WebGPU, with no server-side inference.

Postgres running in the browser through PGlite, paired with an AI assistant for schemas, CSV imports and diagrams.

Turns an uploaded document image into structured Markdown using a vision model.

Generates and interpolates between short melodies and drum patterns using a variational autoencoder in the browser.

Play a few buttons and a neural net turns them into a full piano performance in your browser.

Transcribes piano audio into MIDI notes in the browser using the Onsets and Frames model.

Open-source web chat front end that works with several AI providers using keys you supply.

Clones a voice from a short audio sample and speaks new text in it, using the F5-TTS and E2-TTS models (unofficial demo).