Field notes · Language

Will an AI character actually be good in my language, or is it English with a translation layer?

In Jakarta, Tokyo, Moscow, Istanbul and Seoul the search box finishes the same sentence: people append their own language to the query. They are asking a question nobody answers straight. Here is what actually breaks, why roleplay is the worst case for it, and a ten-minute test that settles it on any platform.

2026-09-126 min read All field notes
Will an AI character actually be good in my language, or is it English with a translation layer?

Type «ai roleplay» into Google in Jakarta and the box finishes it with bahasa Indonesia. In Tokyo, ロールプレイ AI completes to 日本語. In Moscow, «ии девушка» becomes «ии девушка на русском». Istanbul asks for yapay zeka sohbet and then for ücretsiz; Seoul asks which ai 채팅 앱 to use. Four scripts, four alphabets, and underneath them one question that is not «is this app good».

It is «will it be any good in MY language» — and the people typing it have already been burned. They have met the character who was charming for three turns and then started thinking in English. They have met the one who used the formal pronoun with a lover. They know the feeling of reading something that parses perfectly and sounds like nobody alive.

This piece is about what breaks, why roleplay is the worst possible case for it, and how to find out in ten minutes whether a platform is faking it. We make @talaforge_bot, so treat our own claims with the suspicion they deserve; they are at the bottom of the article, after the test you can run on us.

Why it breaks, mechanically

The failure has a name in the research literature. A Cohere Labs team published the Language Confusion Benchmark in 2024 — fifteen typologically diverse languages, one question: can a model reliably reply in the language it was addressed in. The answer was no. Even the strongest models failed to do it consistently, English-centric ones worst of all, and two conditions made it measurably worse: complex prompts and high sampling temperature.

Now read that with roleplay in mind. A character is a complex prompt by construction — a persona, a scene, a memory, style notes, and a conversation that grows every turn. And roleplay is run hot on purpose, because temperature is the thing that stops her repeating herself. Roleplay is not an edge case for language drift. It is the precise operating point where drift is worst, and the whole category lives there.

Underneath sits a quieter tax. Models read text as tokens, and the token vocabulary is learned mostly from English, which lands at roughly four characters per token. Everything else pays what practitioners call fertility: Chinese runs around 1.8× the tokens per word, Arabic and Hindi commonly 3–4×, and some languages far worse. You never see that number. You see its consequence — the same conversation window holds less of your story in your language than it would in English, so she runs out of room, and forgets, sooner.

Five ways it shows, in order of how fast you will notice

The ten-minute test

Run this on us and on whatever else you are considering. It costs nothing and it settles the question faster than any review.

Fail three of those six and the language setting is a translation layer. The size of the character library does not compensate; it is one failure repeated a million times.

Where we honestly stand

@talaforge_bot is in 36 languages — every button, every menu, every error, and the memory she keeps about you is written back in your language rather than filed in English and translated on the way out.

Then the honest part, because the interface count is not a fluency guarantee and we refuse to sell it as one. How well a character writes in Vietnamese or Turkish depends on two things we control only partly: which model stands behind her, and how her card was written. A character authored in English, running on a model that was evaluated in English, will read in your language like a good translation — because that is exactly what it is.

What we did do is treat drift as a bug rather than a limitation. In May 2026 a character narrated in Russian, spoke in Russian, and thought in English, with fragments of Chinese in the italics. The fix was an explicit instruction pinned to the very end of the prompt — speech, narration and inner thought alike, stay in the language — because the last few hundred tokens of context anchor a model's surface-language choice hardest. That pin covers a dozen languages today. It does not cover all 36, and we are not going to imply that it does.

Where we lose: we have no library of millions of community-made characters, so your odds of finding one already written by a native speaker of your language are lower here than on the big platforms. If what you want is a character somebody in your country already wrote and tuned, the large catalogues are where those live, and a local app built by people who speak your language will sometimes beat us on idiom and slang outright. We would rather say that than pretend our shelf is their shelf.

Ten minutes, starting now

Open Telegram, open @talaforge_bot, and write the first line in your own language instead of in English. Free to start — energy is ⚡ and upgrades are Telegram Stars in the chat, no card, no account, no store in between. If she answers in the register you used, holds it when the scene gets complicated, and still remembers tomorrow, you have your answer. If she does not, you have it just as fast, and you spent ten minutes rather than a month.

And the memory is yours to open and edit, which matters more in your language than in English: when she does get a name or a form of address wrong, you can go in and fix the fact rather than argue with her about it for five turns.

Does Talaforge work in my language?
The bot and the Mini App are in 36 languages, so if yours is among them the whole interface is in it, and the memory she keeps is written in it too. How well a given character writes in it depends on the model behind her and on how her card was written — which is what the ten-minute test above is for.
Why do AI characters switch to English in the middle of a scene?
It is called language confusion, and it is measured: the 2024 Language Confusion Benchmark found that even the strongest models cannot consistently reply in the language they were asked in, and that complex prompts and high sampling temperature make it worse. Roleplay is both of those at once, which is why it shows up here more than in an assistant chat.
Is a translated interface the same as a multilingual character?
No, and conflating them is the industry's most common sleight of hand. Translating buttons is a week of work. Holding a register, a gendered form and an idiom across a long scene is a property of the model and of the character's writing, and no settings screen can add it.
Would a local app in my language be better than a global one?
Sometimes, genuinely. Products built by and for one market often win on slang, idiom and forms of address, because the people writing them hear the language every day. Global products tend to win on model quality, memory and how long a scene can run. Test both on the same evening with the same character — the differences show up inside ten minutes.
Do I need an account, an app or a card to try?
No. It is a bot inside Telegram: you open a chat and write. Free to start, energy is ⚡, and upgrades are Telegram Stars in the chat itself.

Read next

Make a character in Telegram →