AI Text Summarizer

How it works

1. Step · 01

   Paste any article, email or transcript up to a few thousand words.

2. Step · 02

   The first run downloads the open-source DistilBART-CNN model (~150 MB) — cached forever after that.

3. Step · 03

   The summary is generated locally on your device and never leaves your browser.

Frequently asked questions

Which model does it use?

Xenova/distilbart-cnn-6-6, an open-source distilled BART fine-tuned on the CNN/DailyMail news dataset. Runs locally via @huggingface/transformers.

How big is the download?

Around 150 MB on the first run. It's cached in your browser after that, so subsequent summaries are instant.

What language does it support?

DistilBART-CNN is English-only. For other languages, paste an English translation first.

Is my text uploaded anywhere?

No. Once the model is downloaded, inference happens 100% in your browser — your text is never sent to a server.

Are my files uploaded to a server?

No. Files are processed directly in your browser using JavaScript and WebAssembly. Nothing is uploaded to our servers, so your documents never leave your device.

Does it work on mobile?

Yes. The tools run in any modern browser on desktop, tablet, or mobile (Chrome, Edge, Safari, Firefox). Very large files may be slower on low-end phones.

• How to Use Claude AI Pro Features for Free (2026)What Claude Pro actually adds, the legitimate ways to get more AI capability at no cost in 2026, and free browser tools that cover common paid-AI tasks.7 min read