Dilinga
ENTR
Get in touch

Language technology · a product by AYARUX

Live translation for calls, messages and camera.

Dilinga is a translation app in development for iPhone and Android. A message leaves in your language and arrives in theirs. A call is translated while it is being spoken. The camera reads the sign in front of you and answers questions about it. Nothing is copied, pasted or carried from one app to another — the conversation is the app.

Ask about Dilinga See what it does

In development. Write to us and we will let you know the day it opens.

Dilinga chat screen: each message shown in the reader's own language.
Dilinga translation screen: text typed in English shown translated into Japanese.

Dilinga translation features

Messages

Both sides write the way they always do. Each one reads their own language.

Calls

Voice and video calls translated while they are being spoken, not afterwards.

Camera

A menu, a label, a form. Point the camera, read it, ask about it.

Your own voice

The translation can be spoken in the speaker's own voice rather than a stranger's.

Calls

Live voice and video call translation

Start a voice or video call the way you would with anyone else. Each sentence is recognised as it is spoken, translated, and delivered to the other side out loud — while the conversation is still going. Both people keep speaking their own language and neither has to wait for a turn.

  • Voice and video, on iPhone and Android
  • Translated speech arrives during the call, not after it
  • Live subtitles on screen while the camera is on
  • Speech is recognised on the device — raw audio is not shipped off for translation
Dilinga contacts screen with call and video buttons next to each person's language.

Face to face

Face-to-face conversation translation

Continuous conversation keeps listening to both sides and translates each turn as it comes. It is the mode for the taxi, the pharmacy counter and the hotel desk — one phone, two people, no buttons between sentences.

  • Both directions in one screen
  • Read it, or have it spoken out loud
  • Text or speech, whichever the moment calls for
Dilinga continuous conversation screen translating between English and Spanish.

Camera

Camera translation for signs and menus

The camera reads the text in front of you and translates it in place — a station board, a menu, a prescription, a form. Switch to Ask and the same photograph answers questions: what is in it, what it means, what to do next.

  • Signs, menus, labels, documents
  • Detects the language it is looking at
  • Ask follow-up questions about the same photo
Dilinga camera screen reading a Japanese station sign and translating it.

Everything in one place

Multilingual messaging in one inbox

Contacts, conversations and calls sit together, each with the language the other person reads. There is no separate translation app open beside the chat, and nothing has to be pasted between them.

  • Text, voice notes, photos and files
  • The other person's language shown on the conversation
  • Call history and contacts in the same place
Dilinga conversation list showing contacts in Spanish, German and Japanese.

In your own voice

A language you don't speak,
in the voice they know.

A translated call in a synthetic voice stops sounding like you. Dilinga can model the speaker's own voice, so the sentence that arrives on the other side is in a language you do not speak — but in your voice.

Voice modelling is in closed beta. It is opt-in, needs a recorded consent, and can be deleted at any time.

Four things happen,
and none of them leave the app.

01

Write, they read their language

The message is translated on its way out. Both sides write the way they always do.

02

Call and be understood

Speech is recognised on the device, translated, and spoken to the other side during the call.

03

Point the camera at it

The camera reads the text and translates it. Ask answers questions about the same photo.

04

In your own voice

Voice modelling carries the speaker's own voice into the translation instead of a synthetic reader.

Scenes

Four moments with the language out of the way.

The frames are the app running, and the translations in them are its own.

01

“The samples will be there on Wednesday.”

You wrote it in English; Marco read it in Italian. Beyond the EN → IT in the header, neither of you did anything extra — both sides just write the way they always do.

A conversation between English and Italian: the sent message and the reply, both read in English, with the language pair in the header.

02

“Where can I get a good breakfast around here?”

Type it or say it; the translation comes back with a button to have it read aloud. Nothing to copy and carry into another app.

The translation screen: an English question about breakfast and its Italian translation, each with a button to have it read aloud.

03

“34 Street — Penn Station.”

Hold the camera up to the sign. The translation settles over the English text, each line in its own place, so you never look away from the sign to read it.

The subway entrance sign at 34 Street Penn Station in New York, read through the camera: the app has laid the Japanese translation over the English text, each line in its own place.

04

“So where does this train go?”

The same photograph stays open. Switch to Ask and the translating ends, the conversation starts: what it says, what it means, what to do now.

The Ask screen with the same New York photograph loaded and the question box open: what do you want to know about this photo.

The people and the messages are fictional and the New York photograph the camera reads is a stock image; the screens themselves are the app running.

Privacy by design

Your conversation stays yours.

No account for free use

Messaging and calling need no sign-up; the app identifies you with an ID created on your own device. You only link an Apple or Google account when you buy Pro.

Speech recognised on the device

During a call, your phone turns speech into text. It is the text that gets translated — the raw audio of the call is not sent anywhere for translation.

Nothing sold, nothing profiled

No advertising, no tracking SDKs, no analytics profile. Call transcripts stay on the device that made the call.

Read the privacy policy

Frequently asked questions about Dilinga

Can I download Dilinga now?

Dilinga is still in development. Contact [email protected] to hear when it becomes available.

What can Dilinga translate?

Dilinga brings message translation, live voice and video call translation, face-to-face conversation and camera translation into one app.

Does the other person need Dilinga?

For messaging and calls inside Dilinga, both people use the app. Face-to-face conversation uses one phone shared between two people.

Can translations use my own voice?

Voice modelling is in closed beta. It is optional, requires recorded consent and can be deleted at any time.

Support

Tell us which languages you need.

Dilinga is still being built. Write to us about the languages you need it in and what you would use it for — we will let you know the day it opens.

[email protected] About AYARUX