Press conferences
Baian provides AI live interpretation for press conferences, translating the spokesperson’s statement and questions that reach the audio feed. Journalists read or listen on their phones. Organisers can replace agreed interpreter channels without booths or receiver distribution.
How far behind the speaker?About 2.4 seconds with Baian. Lower is better.
How often Baian was preferredOver professional translations · English into each language
The line marks 50%: an even split.
On their own phones
Against interpreters
BaianRuns for the whole session.
InterpretersSwap about every 30 minutes.
BaianNo fatigue, however long it runs.
InterpretersIn one study, meaning errors rose after 30 minutes.
BaianBuilt to translate the speech, not summarise it.
InterpretersIn one study, omitted meaning in 350 of 590 segments.
BaianSeveral languages from one stage feed.
InterpretersOne interpreter team per language.
BaianThe speech and each translation, saved.
InterpretersSeparate transcription needed.
BaianDownload the translated audio afterwards.
InterpretersOnly if someone records the booth.
For your AV team
Phones, venue screens, your livestream or an existing headset system, all from one stage feed. A transcript is saved afterwards.
Connection guide for AV teamsPlanning your event
UN Geneva occasionally uses whispered interpretation for press conferences and high-level private bilateral meetings, serving a very limited audience with or without mobile equipment. Decide whether your briefing needs that small-group format or language channels for the full press room.
The European Council’s arrangements for 24 and 25 June 2021 specified interpretation in English, French, German and Portuguese. Its November 2017 press-centre rules give journalists priority for seats with interpretation headphones. Plan the seats and language access for your own briefing.
Baian can replace agreed interpreter channels with translated text and headphone audio on journalists’ phones. For government briefings, the organiser decides whether certified human interpretation is required. If both services operate, identify which languages each supplies in the press information.
Journalists can read the translation while following the statement or choose audio through their headphones. Make the session link visible to people arriving after the briefing has started.
Rehearse a journalist’s question as well as the spokesperson’s answer. Check that the roaming question microphone reaches the translation feed. Enable Multiple spoken languages before the session starts if the supported speaking languages will change, and test names and terms from the statement.
Confirm Camera Overlay access with the booking, then add its link to OBS as a Browser Source for livestream captions. Translated audio requires its own route. Review the finished streamed picture during a question, then agree how the chair handles any interruption to interpretation.
Customer story · QIYADA, Doha
At Qatar Foundation’s QIYADA conference, attendees scanned the code and followed Arabic and English on their own phones. The interpreter booths were taken down.
Tell us your languages, audience size and sound setup. For up to 10,000 listeners at once, we’ll confirm capacity and support before you book.
Discuss your event ↗WhatsApp Explore audience languages →Caption Tool scored above the translators in Hausa, Swahili, Tamil and Urdu (preferred on 67% to 75% of sentences). Baian’s live interpreter had about the same overall quality in Arabic, Hindi and Korean.
148 English sentences that also have professional human translations. Measures translation quality with Google’s MetricX-24 automatic judge.
Baian ran the test. The human translations come from the public FLoRes-200 set.
Baian worked from the spoken audio; the translators worked from text. We compared scores sentence by sentence and counted a result only when the 95% range did not cross zero and two runs agreed. “About the same” means the test found no clear difference; it does not prove the translations were identical.
Median 2.1 seconds across 53 recordings in 15 languages (1.3 to 2.7 seconds per recording).
How long after a sentence ends its finished translation appears.
Baian, on its production Live service.
Measured on Baian’s production Live service from 13 to 15 October 2026, from the end of each spoken sentence to the finished English line in our captured listener feed. Earlier words in a long sentence wait longer than this. Spoken audio arrives a little after the text and was not measured.
Estimated medians: the speaker’s words appear in their own language about 1.0 seconds after they are spoken, and the first translation covering a word about 2.4 seconds after it.
Estimated from our captured listener feed for the same 53 recordings. The capture is incomplete, so some early previews are missing, and previews can still change before the sentence is finished. Times are measured to the feed, not to a phone screen.
Median 2.69 seconds behind the speaker, across 180 speeches.
About 30 minutes is the recommended turn. Meaning errors rose steadily after 30 minutes on task (pilot study, five professionals).
Part of the meaning was missing in 350 of 590 speech segments.