In-Person

Translate face-to-face on one device

Put one device between two people, take turns speaking, and hear translated voice with captions on the opposite side.

In-Person mode live translation screen with turn controls, captions, and translated voice

What is In-Person mode?

In-Person mode is a shared-device translator for face-to-face conversations. Choose the other language, place the device between you, and take turns speaking.

One device, two sides

Each person gets a screen side oriented toward them, so the device can sit between you during the conversation.

Take turns speaking

Only one person speaks at a time. This keeps the translation direction clear and helps reduce overlap.

Hear translated voice

TolkTime translates each turn into voice for the other person, helping preserve tone and emotion.

Read captions

Each side can follow captions for what was said and what was translated.

You are in control

Choose the language, start and stop turns, and end the session when the conversation is finished.

In-Person mode overview showing two sides of one shared device

How In-Person mode works

Choose the language, take turns speaking, and let each side read and hear the translated result.

In-Person mode setup screen on a shared device

Pricing for In-Person

Start with 10 free minutes. After that, $7.50 adds 60 minutes of In-Person translation time.

10 minutes free

New accounts start with 10 free minutes, so you can try a real face-to-face conversation before adding balance.

1 hour for $7.50

In-Person normally uses balance at 1x, so 60 balance minutes provide about 60 minutes of active In-Person translation after rounding.

Trust and Privacy

TolkTime is built for live translation, not for storing your face-to-face conversations.

Built for live turns

TolkTime processes each spoken turn for live translation. We do not record or store the conversation audio on TolkTime servers.

What we do store

For billing and session history, we store the session duration and the languages used.

Translation can be imperfect

Accents, specialist terms, background noise, unclear speech, and overlapping voices can reduce translation accuracy.

For best results

Face-to-face translation works best when each turn is clear, calm, and spoken by one person.

Speak clearly

Clear speech, a quiet environment, a stable connection, and one speaker at a time improve results. Names, specialist terms, accents, overlapping speech, and background noise can reduce accuracy.

Respect the turn

In-Person mode is turn-based. Only one person speaks at a time, and each turn has a 60-second maximum.

Other modes

In-Person mode is for face-to-face conversations on one shared device. TolkTime also has modes for remote browser Calls and one-way listening.

Live Audio Translator

Listen to speech around you and follow translated subtitles with optional translated voice.

Explore Listener mode

Start translating face-to-face

Choose the language, place the device between you, and take turns speaking.