Proofreader API

Building block for the Web’s Built-in Proofreader API. Corrects grammar, spelling, and punctuation, returning the fully corrected text plus per-issue corrections with offsets into the original input. Session reuse and pluggable result caching included. The React adapter lives at @web-ai-sdk/proofreader/react; see useProofreader.

Usage

import { proofread } from "@web-ai-sdk/proofreader";

const result = await proofread({
  input: "I seen him yesterday at the store, and he bought two loafs of bread.",
  expectedInputLanguages: ["en"],
});

console.log(result.output?.correctedInput);
for (const c of result.output?.corrections ?? []) {
  console.log(c.startIndex, c.endIndex, "→", c.correction);
}

result.output is null when the input is empty; otherwise correctedInput is the corrected text and corrections is the list of per-issue edits.

Options

interface ProofreadOptions {
  input: string;
  expectedInputLanguages?: readonly string[];
  monitor?: (m: CreateMonitor) => void;
  cache?: "session" | "local" | { get, set };
  cacheKey?: string;
  signal?: AbortSignal;
}

Name	Type	Description
input required	string	Text to proofread. Empty / whitespace resolves to { output: null }.
expectedInputLanguages	readonly string[]	BCP-47 languages the proofreader should expect as input. English-only today; see Language support.
monitor	(m) => void	Observe the first-call model download.
cache	"session" | "local" | { get, set }	Opt-in result cache (stores the serialized output).
cacheKey	string	Override the default cache key.
signal	AbortSignal	Abort signal.

Returns

interface ProofreadCorrection {
  startIndex: number;   // inclusive offset into the original input
  endIndex: number;     // exclusive offset into the original input
  correction: string;   // suggested replacement
  type?: string;        // not emitted by Chrome's current build
  explanation?: string; // not emitted by Chrome's current build
}

interface ProofreadOutput {
  correctedInput: string;
  corrections: ProofreadCorrection[];
}

interface ProofreadResult {
  output: ProofreadOutput | null;
  cached: boolean;
}

Rendering corrections in place

The corrections offsets index into the original input, so you can highlight each error by slicing between offsets:

let cursor = 0;
const spans: Array<{ text: string; error: boolean }> = [];
for (const c of output.corrections) {
  if (c.startIndex > cursor)
    spans.push({ text: input.slice(cursor, c.startIndex), error: false });
  spans.push({ text: input.slice(c.startIndex, c.endIndex), error: true });
  cursor = c.endIndex;
}
if (cursor < input.length)
  spans.push({ text: input.slice(cursor), error: false });

Language support

The Proofreader API is English-only today. expectedInputLanguages accepts an array for forward compatibility, but requesting a language the browser can’t proofread causes the native create() to reject, which this wrapper surfaces as ProofreaderUnavailableError. Pass ["en"] or omit the option until more languages ship.

No streaming

Unlike the Writer and Rewriter, the Proofreader has no streaming surface; proofread() resolves once with the full result.

Errors and unavailability

The vanilla proofread() throws ProofreaderUnavailableError when the API is missing:

import { proofread, ProofreaderUnavailableError } from "@web-ai-sdk/proofreader";

try {
  const result = await proofread({ input: text });
} catch (err) {
  if (err instanceof ProofreaderUnavailableError) return;
  throw err;
}

AbortSignal is supported.