A tourist walks into your shop and asks something in German — and you don't speak German. An elderly relative shows up to a doctor's appointment with a specialist who only speaks French. You're in a market in Tokyo and you want to explain you're allergic to nuts. In all three situations the other person doesn't have your app — and yet, with KAIXO Direct, you can understand each other in seconds.

What KAIXO Direct is

KAIXO Direct is an in-person mode inside the KAIXO app. Here's how it works: you open your phone, both of you share that screen, and you take turns talking by holding down a big button in the center. Every time someone releases the button, the other person hears what was just said in their own language, translated and read out loud.

The key detail: the other person doesn't need to install anything. No registration. No QR scan. No phone number exchange. Your phone does the work. To them it's like talking to a speaker that understands.

When it saves the day

Direct is designed for in-person conversations, where you're physically in front of the other person. Some real cases we see:

  • Retail. Helping the foreign customer who walks into a souvenir shop, a wine store, a pharmacy, a bakery. The "how much?" + "is it gluten-free?" + "can you wrap it?" exchange resolves in 30 seconds without the gestures-and-pointing routine.
  • Restaurants and bars. Establishments with international clientele. The menu may be translated — but doubts aren't. "No spice", "shellfish allergy", "to-go"… solved instantly.
  • Healthcare and elderly care. Accompanying an elderly relative to a medical appointment with a specialist who speaks another language. It's one of the use cases we hear about most often as a real game-changer.
  • Trades and services. The Romanian plumber explaining the issue. The delivery driver who only speaks French. The unexpected visitor at your door. Short, technical conversations that have to be understood correctly.
  • Travel. When you're the traveler. Asking directions in Bangkok, negotiating in a market in Istanbul, explaining something to a grandmother in a rural Italian B&B.
  • Meeting someone. That conversation that started on a terrace with someone who doesn't share your language. When you put the phone on the table between you, the rhythm is almost natural.

How it works, step by step

  1. Open KAIXO Direct. In the app header, there's a microphone icon button. Tap it.
  2. Set both languages the first time. Yours (language A) and the other person's (language B). KAIXO remembers this for next time — you won't need to set it again.
  3. Hold down the big button while you talk. Release when you're done with the sentence.
  4. The other person hears in their language. The phone automatically plays the translation through the speaker, with natural-sounding voice. The transcript also appears on screen if they prefer to read.
  5. Their turn. They hold down the same button while they talk, release, and you hear them in your language.
  6. Free conversation. Either of you can talk multiple times in a row. KAIXO automatically detects who is speaking each turn from the configured languages, so you don't have to tap anything extra to "switch speaker".

Tip: put the phone flat on a table or counter between you, screen up. Both people can see the transcripts, and the speaker projects the audio neutrally. It's the position that works best in bars, counters and consultations.

Conversation at an outdoor terrace, two people with drinks on the table
Phone flat on the table between you: the position that works best in bars and counters. Photo: Unsplash.

How it differs from Google Translate "Conversation"

The fair question: doesn't Google Translate already do this? Sort of, but with practical differences that matter in the real moment:

  • Push-to-talk by design. In Direct you hold down the button, release, and it translates. No ambiguity about when each sentence starts and ends. Google Translate's conversation mode tries to detect silences, which fails in noisy spots (bars, markets, consultations with multiple people talking).
  • Automatic speaker detection. KAIXO knows you speak Spanish and the other person speaks French — language alone is enough to identify the speaker. Google needs you to tap the right flag before each turn.
  • Built as a single product. Direct is just one of KAIXO's features. If after the conversation you want to keep in touch via chat or call, you already have that person in the app — without bouncing between Google Translate, WhatsApp, and a piece of paper with a number.
  • Privacy by design. Audio is processed in the moment and not stored on disk after the conversation ends. It's not uploaded to social networks, not published, not shared with third parties.

We're not saying Google Translate is bad — it's a very useful tool. We're saying Direct was built specifically for that conversation with a stranger in front of you, and you can feel it.

Languages, internet and privacy

15 supported languages: Spanish, English, French, German, Portuguese, Italian, Basque, Chinese, Japanese, Arabic, Hindi, Russian, Korean, Turkish and Indonesian. The same set as the rest of KAIXO — if you can chat with someone in their language, you can use Direct with them too.

Internet required. Direct uses the cloud to transcribe, translate and synthesize voice. Wi-Fi or mobile data both work. Without a connection it can't operate — that's an honest limitation of the model, not a bug.

Privacy. Audio is not stored persistently. If you want to clear the visual conversation history, just close the Direct screen. We comply with GDPR and publish the full privacy policy.

Who uses it most

From what we're seeing in these first months:

  • Small businesses in tourist areas. Pamplona, San Sebastián, Bilbao, Barcelona, Seville. Neighborhood shops that suddenly serve more foreigners than locals in July.
  • Caregivers in medical appointments. Adult children of elderly immigrants who no longer remember the language of the country they live in.
  • Tourism professionals. Guides, cab drivers, hostel reception, event volunteers. People with many short, varied conversations a day.
  • Frequent travelers. Especially in Asia and regions where English isn't a lingua franca. Direct + Google Maps offline is the most solid combo.

Getting started

If you already have KAIXO installed, Direct is right there: header → microphone icon. First time you set both languages, and that's it.

If you don't have it yet, install it before the next time you'll be talking to someone who doesn't share your language. It's one of those things that doesn't seem useful until you need it — and then you wonder why you didn't install it earlier.

FAQ

Does the other person need the app? No. That's Direct's central difference. Only your phone.

Does it work offline? No. It needs internet (Wi-Fi or mobile data).

Is there a minute limit? The free plan has a daily cap that's enough for a short conversation. Paid plans offer extended or unlimited minutes.

Is the conversation saved? Not persistently. Audio is processed in the moment and discarded when you close the screen.

Does it work for groups of 3+ people? Direct is designed for 2 languages at a time. For multilingual groups, KAIXO's chat or video call is the right option — every participant receives messages in their own language.