Station

Touch

Platform

LiveDub

Live Translator

Use Cases

Contact

Station

Touch

Platform

LiveDub

Live Translator

Use Cases

Contact

You just talk.
The screen handles the rest.

Sit across from each other with a single device between you, and your conversation is translated both ways, right on the screen. Translation begins the moment you speak—no need to pick a language, press a button, or worry about background noise. Create an account on the Perso platform and start using it for free immediately.

Start for Free

Set it up once after that, it's all conversation.

Set up just once,
and after that, it's only conversation.

No need to pass a microphone or press a button. Listening, translating, and displaying the three steps flow together automatically the moment you speak.

There is no need to pass the microphone, nor is there any need to press any buttons.
The three steps of listening, transferring, and showing
connect automatically the moment you speak.

Speak, and it understands

It automatically detects who's speaking, and in what language. No need to pass a microphone or keep the room quiet.

It captures the whole context.

Instead of waiting for each sentence to end, it interprets as you speak—keeping the natural flow of the conversation intact.

Display it on both screens

Each person views subtitles in their own language. The original text and translation remain side by side.

Two-way interpretation

No buttons, it knows which way the conversation is going.

Hear Korean, and it translates into the other language; hear the other language, and it translates into Korean—all on its own. No more awkwardly passing a translation app back and forth.

It automatically determines the direction of interpretation: when Korean is heard, it translates to the other person's language, and when the other person's language is heard, it translates to Korean.
The awkward moments of passing a translation app back and forth disappear.

Strong against noise

A noisy setting is the default assumption.

It accurately captures your conversation—even over a taxi engine, store music, or airport announcements. With speech recognition built to handle ambient noise, it reduces the need to say "Could you say that again?"

On any screen.

From a small table to a big stage.

The same interpretation flows to the tablet on your table or the big screen in a conference hall. Just swap the screen to fit the venue.

The same interpretation flows on the tablet on the table,
as well as on the large screen in the conference hall.
You only need to change the screen to fit the scale of the venue.

Each reads in their own language

One screen faces two people.
Subtitles fill up almost simultaneously with the speech, leaving the original text and the translation side by side.

One screen faces two people.
Subtitles appear almost simultaneously with the speech,
and both the original and translated texts remain side-by-side.

It works, no matter who the customer is

It understands 32 languages.
It doesn't just choose from prepared languages, it adapts to the language it hears.

It understands 32 languages.
It doesn't just choose from prepared languages,
it adapts to the language it hears.

Review past conversations again.

The counseling and guidance contents are recorded side by side in the original and translated text.
From confirming response quality to providing evidence for disputes.

Consultation and guidance details are recorded side-by-side in both the original language and the translation. From verifying service quality to serving as evidence in disputes.

Does not wait for the sentence to finish

Context-based simultaneous interpretation begins translating while the speech goes on, maintaining the natural rhythm of the conversation.
It is a real-time AI pipeline, just like driving Perso's avatar.

Context-based simultaneous interpretation begins translating while the speech goes on, maintaining the natural rhythm of the conversation.It is a real-time AI pipeline, just like driving Perso's avatar.

Conversations are translated and protected.

Face-to-face consultation is a touchpoint where personal information is exchanged. The entire interpretation process operates under strict security principles.

Transmission Security

All paths through which data travels are encrypted.

Data Protection

Not collecting it is the strongest protection. Audio is used only for interpretation processing.

History Management

The operator manually configures whether to save conversation history and how long to preserve it.

Ask anything.

We provide clear answers to your most frequently asked questions about how Perso Interpreter is transforming on-site face-to-face communication.

Do both people need to install the app?

Does it work even in noisy environments?

Which languages do you support?

Which devices can I use it on?

Does it work without an internet connection?

How much is the fee?

From implementation inquiries
to technical consultation,
and partnership proposals.

A dedicated representative will personally review your request and suggest the optimal direction tailored to your business circumstances. If you are an individual team or on-site department, you can sign up for the Perso platform and start using it for free right now.