Artifacts

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.

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.

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.

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.

Loads a GGUF model with a WebAssembly llama.cpp build and generates text in the browser.

Chat with open language models that download into your browser and run on WebGPU without a server.

Transcribes or translates speech from an audio file, URL or microphone with Whisper running inside the browser tab.

Chat, write, translate and transcribe with AI models downloaded to and run on your device.

Object detection app that runs YOLOv8 with ONNX Runtime Web on images or a webcam stream.

Sample apps and an expression playground for the WebNN API, which runs neural networks on device hardware from the browser.

Streams live microphone audio through Whisper on the GPU in your browser and prints the words as you speak.

Transcribes a recording in the browser and labels which speaker said each segment.

Runs a Gemma 4 model in the browser with custom WebGPU kernels, so chat needs no server.

WebGPU-accelerated Whisper that turns microphone or file audio into text locally in the browser.

Speech recognition with the smaller Distil-Whisper model, executed locally in the browser.

Converts a document page image into structured Docling markup using a 258M model run in the browser.

Points your webcam at a scene and has a small vision-language model describe it continuously, locally on WebGPU.

Chat playground that downloads open models and runs them locally on WebGPU with WebLLM.

Markdown editor web app that edits local files through the File System Access API, with optional in-browser AI.