Text Summarization in the Browser

Condense long documents into concise summaries using DistilBART or Chrome Built-in AI.

What Is Text Summarization?

Text summarization generates a shorter version of input text that captures the key information. Abstractive summarization (used by DistilBART and Chrome AI) rephrases and condenses the original text rather than extracting sentences verbatim. This produces more natural, readable summaries but requires more sophisticated models.

This capability is exposed through the summarize() function in @localmode/core. All processing runs entirely in the browser - no server, no API key, no data leaves the device. After the initial model download, text summarization works completely offline.

Real-World Applications

Article digest and news summary apps. Meeting notes condensation. Research paper abstract generation. Email thread summarization. Document preview generation. Report executive summaries.

These use cases all benefit from local, on-device processing: user data stays private, there are no per-request API costs, and the application works without internet after initial setup.

Getting Started

Install the required packages:

npm install @localmode/core @localmode/transformers

Import the core function and provider:

import { summarize } from '@localmode/core';
import { transformers } from '@localmode/transformers';

The recommended starting model is Xenova/distilbart-cnn-6-6 - it provides the best balance of quality, speed, and download size for most applications.

Code Example

import { summarize } from '@localmode/core';
import { transformers } from '@localmode/transformers';

const model = transformers.summarizer('Xenova/distilbart-cnn-6-6');

const { summary } = await summarize({
  model,
  text: longArticleText,
  maxLength: 150,
  minLength: 50,
});

// With Chrome AI fallback - try Chrome's built-in AI first
import { chromeAI } from '@localmode/chrome-ai';

async function getSummarizer() {
  try {
    return chromeAI.summarizer();
  } catch {
    return transformers.summarizer('Xenova/distilbart-cnn-6-6');
  }
}

This example demonstrates the core workflow: create a model instance from the provider, call the summarize() function with your input, and receive structured results. The same pattern works identically across all 2 available providers: Transformers.js, Chrome Built-in AI.

Available Models

The following models support text summarization through LocalMode. Choose based on your target device, acceptable download size, and quality requirements.

Model	Provider	Size	Speed	Quality
Xenova/distilbart-cnn-6-6	Transformers.js	~284MB	Medium	High
Xenova/distilbart-cnn-12-6	Transformers.js	~422MB	Slow	Higher
chrome-ai:gemini-nano-summarizer	Chrome Built-in AI	0MB	Fast	Good

Choosing a model: For most applications, start with the recommended model (Xenova/distilbart-cnn-6-6). If download size is the primary constraint (e.g., mobile PWA, browser extension), pick the smallest model that meets your quality bar. If quality is the priority (e.g., enterprise search, content analysis), use the largest model your target devices can handle.

Cloud vs Local: Cost and Privacy Comparison

Running text summarization locally eliminates per-request API costs and keeps all data on-device. Here is how the economics compare:

Service	Cost / Notes
LocalMode	gives you both options at $0 ongoing cost

Cloud summarization uses general-purpose LLMs at $2-10 per million tokens. Dedicated summarization models like DistilBART are faster and cheaper for this specific task. Chrome AI summarization is instant and free in supported browsers. LocalMode gives you both options at $0 ongoing cost.

The break-even point for most applications is low: if you process more than a few hundred requests per day, local inference costs less than any cloud API within the first week. For privacy-sensitive applications (medical records, legal documents, financial data), the cost comparison is secondary - the ability to process data without it ever leaving the device is the primary value.

Available Providers

Transformers.js - ONNX-optimized models via ONNX Runtime Web. Supports both WebGPU and WASM backends. Broadest model catalog for non-LLM tasks.
Chrome Built-in AI - Chrome Built-in AI (Gemini Nano). Zero model download. Available in Chrome 138+ with flag.

AbortSignal Support

All summarize() calls support cancellation through the standard AbortSignal API:

const controller = new AbortController();

const promise = summarize({
  model,
  text: 'input text',
  abortSignal: controller.signal,
});

// Cancel if needed (e.g., user navigates away)
controller.abort();

This is essential for responsive UIs - cancel in-flight operations when the user navigates away, submits a new query, or closes a dialog. The underlying model inference stops immediately, freeing memory and compute resources.

React Integration

If you are building a React application, @localmode/react provides hooks that manage loading states, error handling, and cancellation automatically:

npm install @localmode/react

import { useSummarize } from '@localmode/react';

The hook returns { data, error, isLoading, execute, cancel, reset } - providing everything a UI component needs to display progress, handle errors, offer cancellation, and reset state.

Nlp Specialized - model guide
Chrome Ai - model guide
Text Generation - task guide
Text Embeddings - task guide

Methodology

All function signatures, hook return shapes, model IDs, and provider API calls were verified directly against the LocalMode monorepo source: packages/core/src/summarization/summarize.ts and types.ts, packages/transformers/src/implementations/summarizer.ts, packages/transformers/src/models.ts (SUMMARIZATION_MODELS constant), packages/chrome-ai/src/implementations/summarizer.ts, and packages/react/src/hooks/use-summarize.ts plus core/use-operation.ts. The model table was corrected to exactly match the SUMMARIZATION_MODELS catalog (two Transformers.js models) plus the Chrome AI summarizer whose modelId is chrome-ai:gemini-nano-summarizer. Three models that appeared in the original table (onnx-community/ModernBERT-base-ONNX, Xenova/bert-base-uncased, Xenova/distilbert-base-cased-distilled-squad) belong to fill-mask and question-answering catalogs, not summarization, and were removed. Cloud pricing figures are general guidance and subject to change - verify current pricing with each provider before making cost decisions.