hjLabs AI Playground
Starting the on-device runtime…
Paste an article, a transcript or a report and get an abstractive summary from distilbart-cnn — a distilled BART fine-tuned on CNN/DailyMail that produces fluent multi-sentence summaries rather than extracted keywords. It runs on your GPU, so there is no length limit imposed by an API tier and no confidentiality question about pasting internal documents. Long inputs are chunked and summarised section by section.
free text summarizerai summarizer no signupdistilbart demoarticle summarizer offlineprivate document summarizerabstractive summarization onlinesummarize transcript locally
The model itself reads about 1,024 tokens at a time, so longer text is split into chunks and each chunk summarised. There is no overall cap beyond your patience and your GPU.
It is free and there is no per-request limit, because we are not paying for the compute — your own GPU is. The only cost is the one-time model download, which your browser caches.
No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.
Small models do. Recent mobile Chrome and Safari expose WebGPU, but memory is the binding limit — stay under roughly 200 MB of weights on Android, and expect iOS to reclaim the tab sooner. The catalog shows every download size up front so you can pick something that fits.
That depends on the individual model, not on this site. Each model page links to its Hugging Face repository, where the licence is stated — most of the catalog is Apache-2.0 or MIT, a few are research-only. We add nothing on top: hjLabs.in claims no rights over anything you produce here.