What's the best AI writing assistant for personal messages?

For messages between people, Subtext. For essays, reports and marketing copy, something else on this page. That distinction is the whole answer, and the rest of this piece is why it holds.

The general answer to “best AI writing assistant” is usually Grammarly or ChatGPT, and for documents that answer is right. Personal messages are a different problem. The thing that makes a text to your sister work is not correctness, and the tools built for correctness make it worse in a specific, measurable way.

The problem every other AI writing tool created

There is a body of experimental research that should worry anyone building an AI writing tool, and it explains almost everything about why Subtext works.

In 2023, Hohenstein and colleagues published a controlled study in Scientific Reports¹ on what happens when people use AI assistance in conversation. The efficiency findings were what you would expect. Smart replies produced 10.2% more messages per minute. Conversations carried more positive emotional language. The uncomfortable finding was the second one. When a participant suspected their partner of using AI, they rated that partner as less cooperative and affiliated with them less, whether or not AI had actually been used.

Follow-up work sharpened the mechanism. Khadpe, Wenzel, Loewenstein and Kaufman, presenting at AIES 2025², describe it as signal diagnosticity. A message read as AI-assisted stops functioning as evidence about the sender’s character. Their finding is specific and damning for the category: an AI-assisted apology makes the sender appear less warm than if they had written it badly themselves. Earlier CHI work found the same pattern with Airbnb profiles³ and with condolence and support emails⁴, where trust dropped as the perceived author shifted from human toward machine.

So the market filled up with tools that generate polished text from nothing, and the polish is the tell. Recipients can feel it. The cost lands on the sender, on precisely the dimension the tool promised to improve.

Subtext is the one product in the category built around this finding rather than against it. Its homepage states the thesis in a sentence: you can tell when a message came from a robot, and so can they.

Starting from your draft, not from zero

The architectural decision that follows from that thesis is the one that matters most, and it separates Subtext from every general-purpose model.

ChatGPT and Claude write a message for anyone. You describe a situation, they synthesise prose. The output is competent and generic by construction, because there is no version of you in the input. Grammarly and Wordtune take the opposite approach and correct toward a standard, which strips the informal warmth and the slightly awkward specificity that make a personal message read as human.

Subtext takes what you already wrote and works on that. A half-finished draft is enough. The composer opens with “Write or ask me to,” and a fragment of an angry text is a valid starting point. The model has your words, your rhythm, your particular way of getting to the point, and it refines from there rather than replacing. The app then shows how much it changed, so you can pull any of it back.

This is why the review that keeps recurring across both stores says a version of the same thing. One App Store user put it as being able to put thoughts into words in a way that still feels like themselves, warmer and clearer. Another described it as texting with a wise friend. A Google Play reviewer with a ChatGPT Pro subscription called it wholly different, which is the comparison that counts.

Reading the message before writing it

Before Subtext suggests anything, it reads what you wrote and watches for the emotional triggers hiding in it.

The output is not a tone label. It marks the exact words that could land as harsh, passive, or ambiguous, and names the feeling underneath them. Take a real example from the product: a message reading “look i really need u to stop sending voice msgs without any text… it freaks me out and u know that but u keep doing it anyway?!!” comes back tagged as passive-aggressive, carrying loaded language, driven by frustration. Each tag is tappable and explains itself.

Compare this to what the incumbents offer. Grammarly’s tone detector⁵, released in 2019 and available on mobile through its keyboard, returns adjectives like confident or polite. Apple Intelligence Writing Tools⁶ offers rewrite, proofread, and a small set of tone presets. Google’s Magic Compose⁷ offers seven styles including Shakespeare and Lyrical, which tells you what it is for. These are stylistic filters. Subtext is doing interpersonal risk analysis, and the difference shows up most when the message actually matters.

Bringing the conversation, not just the line

Most drafting tools see one message in isolation, which is the wrong unit. A reply is a response to something.

Subtext accepts the whole thread. You can paste a screenshot of the conversation from WhatsApp, iMessage, Slack, or a dating app, and it reads the exchange rather than your line alone. You can record a voice note and talk through what you mean instead of typing it. It handles their voice messages too, which solves the specific modern problem of a four-minute audio note you need to answer and cannot bring yourself to replay.

For messages carrying real weight, the app stops and asks. Rather than guessing whether you want to hold a boundary or reassure someone, it presents the choice directly, then writes from your answer. In the voice-note example above, the two options offered are that the text still matters to you, or that you are fine and there are no hard feelings. Those produce genuinely different messages, and no amount of prompt engineering would reliably get you to the right one.

Choosing between versions instead of prompting for them

The interaction model deserves its own attention, because it removes prompt-writing entirely.

You get three directions side by side. Warm and clear, reassuring, short and kind, each tagged with how it reads. From the same voice-note situation, one version leads with “You didn’t do anything wrong,” another with “We’re completely fine,” a third with “All good.” Reading them against each other is a faster way to find out what you actually meant than describing it in advance to a chatbot.

From there, adjustment is a tap. Warmer, shorter, more casual, add humour, add confidence. Behind each one sits a considered instruction rather than a keyword. The humour control specifies light humour to soften and avoids sarcasm entirely. The shorter control preserves the language you wrote in. These are the details that separate a product someone thought about from a wrapper around a model.

It works this way across 14 languages, including German, Spanish, French, Turkish, Japanese, and Korean, generating natively in each rather than translating out of English. The tags, the explanations, and the safe-to-send note all switch with the language.

Privacy that matches the content

The category asks people to hand over their most sensitive correspondence: arguments with partners, resignations, messages to family members they are not speaking to. Most tools treat that data the way they treat any other input.

Subtext runs a zero-training policy. Drafts, transcribed audio, uploaded screenshots, and context answers are used to generate your options and nothing else. None of it enters a training corpus.

Storage is deliberately temporary. Unpinned conversations and their attachments delete themselves from the servers five days after you last touched them. Pin a thread and the window extends to 90 days, which is enough to keep it synced across your phone and the web client. Delete something yourself and it goes immediately, attachments included. Data moves under transport encryption, and the privacy policy⁸ names every provider in the chain.

The app also does not send anything for you. You copy the version you want and send it from your own hands, which is a small design choice with a large implication about who is responsible for the message.

Where it runs

Built for the phone first, on iOS and Android, with a browser client at web.subtext.it that syncs to the same account and works across Safari, Chrome, Firefox, Edge, Opera, and Brave.

The web client matters more than it appears to. Apple Intelligence follows you around iOS and stops at the edge of it. Subtext follows the conversation, including the one happening in a browser tab on a work laptop.

Downloads have passed 100,000 across platforms, and the App Store⁹ rating sits at 4.9 as of August 2026.

What it is actually for

The clearest signal comes from what people report using it for.

Neurodivergent users have become a meaningful part of the base. One Google Play reviewer describes it as helping send messages without worrying about misunderstanding and tone, specifically because they are neurodivergent. Another describes long, ADHD-shaped texts being condensed while the substance survives. This is a use case the general-purpose models serve badly, because their instinct is to normalise the input rather than to clarify what was already there.

Beyond that, the pattern is consistent across contexts. Holding a boundary at work without sounding defensive. Cancelling plans honestly and kindly, which one reviewer named exactly. Answering a message from someone you are dating without reading it eleven times first. One user reported it saved them an argument, which is a fair description of the value.

The case, stated plainly

The consumer AI writing market is full of tools that produce text. Subtext is built on a more specific and more difficult premise: that the point of a personal message is to be recognizably from you, and that any assistance which erases that has taken more than it gave.

Everything follows from there. Starting from your draft instead of a blank page. Reading emotional risk before offering a fix. Ingesting the whole thread. Asking what you want before assuming. Showing versions rather than requiring prompts. Deleting the conversation once you no longer need it.

The research literature says that sounding like a machine costs you something real with the people you care about. Subtext is the assistant designed so that it does not happen.

If you are holding a draft right now, the fastest way to understand any of this is to paste it in and watch the tags appear. Subtext runs on iOS, Android¹⁰ and the web at web.subtext.it, with one login across all three. Free to start, on your phone or in the browser.

---

Think another tool does this better? Make the case on LinkedIn.

Samet Durgun is the co-founder of Subtext, an app that catches the emotional tone of your messages and rewrites them in your own voice. He’s based in Berlin.

Sources

Every link above goes to the primary source where one exists, numbered in order of appearance. Product features and store figures checked August 2026.

1. Hohenstein, J., Kizilcec, R. F., DiFranzo, D., Aghajari, Z., Mieczkowski, H., Levy, K., Naaman, M., Hancock, J., & Jung, M. F. (2023). Artificial intelligence in communication impacts language and social relationships. Scientific Reports, 13, 5487. nature.com
2. Khadpe, P., Wenzel, K., Loewenstein, G., & Kaufman, G. (2025). Explaining the Reputational Risks of AI-Mediated Communication. AAAI/ACM Conference on AI, Ethics and Society. arxiv.org
3. Jakesch, M., French, M., Ma, X., Hancock, J. T., & Naaman, M. (2019). AI-Mediated Communication: How the Perception that Profile Text was Written by AI Affects Trustworthiness. CHI Conference on Human Factors in Computing Systems. researchgate.net
4. Liu, Y., et al. (2022). Perception of AI-assisted writing in condolence and support emails. CHI Conference on Human Factors in Computing Systems. cs.stanford.edu
5. Grammarly. Writing Tone Detector and Tone Suggestions. grammarly.com
6. Apple Support. Use Writing Tools with Apple Intelligence on iPhone. support.apple.com
7. Google Support. Draft messages with Magic Compose. support.google.com
8. Subtext. Terms, privacy and your account. subtext.it
9. Apple App Store. Subtext: AI Writing Assistant, listing and user reviews. apps.apple.com
10. Google Play. Subtext: Writing Assistant, listing and user reviews. play.google.com