Government summits
Baian provides AI live interpretation for government summits through delegates’ phones. Organisers decide whether certified human interpretation is required. Baian can run alongside interpreters or replace the booth setup where the event permits it.
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 interprets statements made in any of the six official UN languages into the others. Its guidance asks speakers to provide written statements in advance and speak at a pace interpreters can follow. Collect the language needs of your delegations before deciding which audience channels to provide.
UN Geneva occasionally uses whispered interpretation for high-level private bilateral meetings with a very limited audience. Plan these separately from plenary interpretation. The organiser decides whether any part of the summit requires certified human interpretation.
Baian can replace the interpreter team and booth for agreed channels, with delegates using their own phones and headphones. If the summit retains human interpretation, tell each delegation which channels Baian supplies and how delegates should find them.
At Qatar Foundation’s QIYADA in Doha on 25 and 26 September 2026, attendees followed Arabic and English on phones. Baian’s event team confirms that the interpreter booths were taken down and no translation headsets were distributed.
The QIYADA interpretation setup ↗Rehearse the chair’s microphone and the microphones delegates will use for questions. Check that an unscripted exchange reaches the translation channel as clearly as a prepared statement. Include diplomatic titles and the names of the delegations in that test.
Before the session starts, enable Multiple spoken languages if the chair and delegates use different supported languages. Test a handover from a speech to a question while a reviewer stays on the same audience channel. Agree how the chair will handle any interruption to interpretation during the summit.
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.