# Longpipe > Open-source SDK for real-time video effects in the browser: virtual backgrounds, > background blur, portrait matting, face touch-up, auto-reframe, and microphone > noise removal. Runs custom-trained models as hand-written WebGPU/WebGL2 shaders > in a fully-GPU, zero-copy pipeline — no general-purpose inference runtime. > MIT licensed (source and model weights). npm: `longpipe`. ## Essentials - Install: `npm install longpipe` - Public class: `EffectsPipeline` (NOT `Pipeline`) — `import { EffectsPipeline } from 'longpipe'` - Hand it a `MediaStream`, get a `MediaStream` back: `new EffectsPipeline(stream, options)` - Construction is synchronous; `pipeline.stream` is available immediately and emits unprocessed passthrough until `pipeline.ready` resolves. - Model weights stream from `https://cdn.longpipe.dev/models/v/0.0.5/` by default; self-hostable. - Browsers: Chromium, Firefox, Safari (desktop + iOS). WebGPU when available, WebGL2 fallback. - Five model presets (`xs`, `small`, `medium`, `large`, `xl`); `preset: 'auto'` benchmarks the device at init and an adaptive controller swaps presets at runtime. - Backgrounds, touch-up and auto-reframe share ONE encoder pass — enabling a second effect does not cost a second inference. Audio denoise is a separate AudioWorklet pipeline. ## Docs - [Longpipe docs](https://longpipe.dev/docs): Open-source video effects SDK — overview and quick links - [Getting started](https://longpipe.dev/docs/getting-started): Install Longpipe and add your first effect - [API reference](https://longpipe.dev/docs/api): EffectsPipeline class reference - [Architecture](https://longpipe.dev/docs/architecture): How Longpipe works — one encoder, many heads, and a fully-GPU pipeline - [Backgrounds](https://longpipe.dev/docs/backgrounds): Accepted background input formats - [Touch-up](https://longpipe.dev/docs/touchup): Face touch-up (skin smoothing) — options, styles, and how it composes with backgrounds - [Auto-reframe](https://longpipe.dev/docs/reframe): Auto-reframe — framing the subject automatically, in auto or manual mode - [Audio denoise](https://longpipe.dev/docs/audio): Real-time speech denoising (DeepFilterNet3 / RNNoise) - [Presets & autotune](https://longpipe.dev/docs/presets): Model size knobs and how autotune picks one - [Browser support](https://longpipe.dev/docs/browser-support): Minimum browser versions for Longpipe on Windows, macOS, Linux, Android and iOS, how it runs on both WebGPU and WebGL2, and how frames get in and out of its worker on each browser. - [Models](https://longpipe.dev/docs/models): Longpipe's own models vs MediaPipe's selfie segmenter inside Longpipe - [Performance & quality vs MediaPipe](https://longpipe.dev/docs/benchmarks): Longpipe vs MediaPipe selfie segmentation in the browser, on speed (FPS on WebGPU and WebGL) and matte quality (P3M-10k), with reproducible benchmark code - [Model layer](https://longpipe.dev/docs/model-layer): Run the Longpipe matting model directly, without the pipeline - [ONNX & other runtimes](https://longpipe.dev/docs/onnx): Official ONNX exports of the Longpipe models for Python, native apps, servers and onnxruntime-web - [Self-hosting weights](https://longpipe.dev/docs/self-hosting): Point Longpipe at your own model weight CDN - [Datasets & licensing](https://longpipe.dev/docs/licensing): MIT license for SDK and weights, and the training data behind the models ## Full text - [All documentation as one file](https://longpipe.dev/llms-full.txt): every page above, concatenated as plain markdown. ## Source - [GitHub](https://github.com/sb2702/longpipe): SDK source, training code, model export. - [npm](https://www.npmjs.com/package/longpipe) - [Live demo](https://longpipe.dev/demo)