AI Paraphraser
Paraphrase text four ways: formal, casual, shorter, or longer, with a small language model that does the rewriting on your own graphics card.
Runs entirely in your browser — your files and text never leave your device. The AI model downloads the first time you run this tool, then stays on this device — so later runs work offline.
Downloads the language model (~543 MB) the first time you run it, then works offline.
The rewriter is a small language model that runs on your graphics card, so it needs Chrome, Edge, Safari 26, or a recent Firefox with WebGPU. It downloads once (~543 MB) on first use, then works offline. Longer text is rewritten paragraph by paragraph, streaming as it goes.
How to use
- Type or paste into Text to rewrite. One awkward sentence is a perfectly good input, and so is a three-paragraph draft.
- Choose from Rewrite as. Formal is preselected, and the four settings are four different instructions to the model rather than positions on a slider.
- Press Rewrite. The first press fetches the model, roughly 543 MB, with the percentage shown in the status line beside the button. Cancel sits next to it throughout.
- Read what lands in the Rewrite box, press Rewrite again if the wording missed, then use the copy button beside the Rewrite label.
How the rewriting works
Rewriting your own sentence is oddly hard. You already know what it means, so every attempt comes back the same shape as the first one. A paraphrasing tool helps here for a dull reason: the model has no attachment to your draft. Hand it the line, choose a target, and read a version somebody else would have written.
Rewrite as holds four options and opens on Formal. Formal asks for complete sentences, precise vocabulary, and no contractions. Casual asks for the reverse, simple words and a friendly tone. Shorten is told to cut extra words and unnecessary detail while keeping every main idea. Expand is told to add examples, clarifications, and context to something too terse to stand on its own.
Qwen3-0.6B does the writing, a small instruction-tuned language model that runs on your graphics card through WebGPU. It arrives once as a 543 MB download and then lives in the browser cache. Chrome, Edge, Safari 26, and current Firefox can reach a GPU. Where the browser or the card falls short, the Rewrite button is disabled as the page loads and the message names which of the two is missing.
Longer text is never fed in whole. The planner cuts at paragraph breaks first, then at sentence ends, aiming for pieces of about 150 words. Each piece is a separate pass, the status line counts them off as it goes, and the Rewrite box fills in while you read. Blank lines between your paragraphs are recorded before the split and put back afterwards.
Sampling is switched on at temperature 0.7. Run the same paragraph twice and the two rewrites will part company inside the first line, which is the point: make three and keep the one that sounds like you. Read it back before it goes anywhere, because 0.6 billion parameters is small enough to drop a qualifier without noticing.
One blunt line, made formal
Start with a Slack-grade sentence: “Can't do the Tuesday call, move it.” Leave Rewrite as on Formal and press Rewrite. Seven words in means the token budget lands on its floor of 64, which is still several times the room the answer needs, so nothing gets truncated.
Back comes one polite sentence, along the lines of “I am unable to attend Tuesday's call and would like to reschedule it.” Press Rewrite again and the wording shifts, because the decoder samples rather than always taking its top guess. Switch to Expand and you will get a reason for the change invented for you, which is precisely the moment to edit instead of copy.
Good to know
- Chunks are rewritten independently, so the model never sees the piece before the one it is working on. That is where meaning drifts: a pronoun loses the thing it referred to, a term you defined in the opening comes back undefined, and a comparison loses its other half. Anything over 150 words deserves a careful read at the joins.
Frequently asked questions
Why is the Rewrite button greyed out?
Your browser could not hand the page a GPU. There is no processor fallback here on purpose, since a weaker model tends to invent rather than rephrase. Chrome, Edge, Safari 26, and recent Firefox all work. Some GPUs pass the WebGPU check but lack 16-bit shader support, which this model needs, and the message tells you which of the two cases you hit.
What is the real difference between Shorten and Expand?
The instruction, and the room the model is given. Shorten gets a budget of roughly 1.2 times the input length and is asked to strip padding while keeping every idea. Expand gets about three times the input and is asked for examples and extra context. Both are capped at 768 new tokens per chunk, so a very long piece cannot run away.
Will a rewrite from here get past an AI detector?
I would not build anything on that assumption. The output is written by a language model, so a detector looking for machine text has every reason to flag it. Disguising authorship is the wrong job for this page anyway. What it is good at is handing you a second phrasing of your own sentence to choose from.
Why does the same paragraph come out different every time?
The decoder picks each word from a probability distribution instead of always taking the most likely candidate, at temperature 0.7 with top-p 0.8. Two runs diverge almost immediately. Treat it as a drafting feature: three passes give you three versions to pick between.
How much text can I put in?
The box has no ceiling. What grows is the work. Twelve hundred words gets planned into roughly eight chunks of 150, each one a separate trip through the model, and the status line counts them off so you can see how far along it is.
Do my paragraph breaks survive?
They do. The planner notes which chunk ended each paragraph before any rewriting starts, and the reassembly puts a blank line back at exactly those positions. Sentence splits inside one paragraph rejoin with a single space, and stray spaces before commas and full stops get tidied up.
Why is the first rewrite so much slower than the rest?
Two things have to finish before a single word appears. The 543 MB model downloads, then it is compiled into shaders for your particular card. Neither happens again. From your next visit the file comes from cache and the page keeps working with the network off.
Can I rewrite one sentence in the middle of a paragraph?
Not from the box as it stands. Paste that sentence on its own, rewrite it, and drop it back into your document. Paste the whole paragraph and every sentence in it is fair game, so the model will cheerfully reword the parts you were happy with.
Missing something in AI Paraphraser? Suggest a feature →