Live captions
Live captions on every screen in the room.
The speaker’s words appear as text on your venue screen, your livestream and attendees’ phones, in their language, a translation, or both. No app to download.
- Audience phonesRead or listen after scanning a QR code.
- Venue screensLive captions on a projector or LED wall.
- LivestreamA caption overlay for OBS.
- Headset systemTranslated audio through an audio interface.
- TranscriptThe whole session, saved afterwards.
New to live captions?
Captions or translation?
Captions show the speaker’s words in their own language. Translation shows the same speech in another language. Baian can show either, or both.
What is live captioning? A simple guideSetup
How do we set it up?
Three steps, then open the Projector link on the screen computer or add the Camera Overlay link to OBS.
- 01
Connect the stage audio
Plug the sound desk into a laptop by USB, or use an audio interface.
- 02
Open Baian on a laptop or tablet
Choose your languages and press start.
- 03
Share the QR code
Attendees scan it and follow on their own phones.
Results
How accurate is it?
- Against interpretersAbout 2.4 seconds behindOur estimate for Baian. A separate study measured human interpreters at 2.7 seconds.How we measured
- Against translatorsAbout the same, working liveIn Arabic, Hindi and Korean. Baian heard the speech; the translators had the text.How we measured
- Against other AI1st in live Arabic and KoreanOn the same speech tests as OpenAI, Google and ElevenLabs.How we measured
Questions
Questions about live captions.
Do attendees need to download an app?
No. They scan a QR code or open a link, choose a language and read in their phone’s browser. There’s no account to create.
How do we show live captions on a conference screen?
In Baian’s sharing panel, choose Projector and open its link on the computer driving the screen. You can change the text size, colours and QR code position. Changes there don’t affect attendees’ phones.
How do we add live captions to a livestream?
Copy the Camera Overlay link from Baian and add it to OBS as a Browser Source over your camera scene. The overlay uses the caption style you saved in Baian. Translated audio needs its own audio route. Confirm Camera Overlay access with your booking.
Can the captions be translated?
Yes. Show the speaker’s own language, a translation, or both. Attendees can also pick their own language on their phones at the same time.
How fast do captions appear?
In our recordings, captions in the speaker’s own language appeared about 1 second after each word, and the first translated text about 2.4 seconds after. Both are estimates, and the translated text can change slightly as the speaker continues.
Hear it with your own event audio.
Bring a short recording, your languages and your audience size. We’ll show you the listener experience.
Arrange a demo WhatsAppSources and methodsEvery number on this page, with its test and date
- Live speech recognition (AssemblyAI real-time benchmark)AssemblyAI runs 25 August to 23 September 2026; Baian runs 13 to 15 October 2026
1st in Arabic (5.1%) and Korean (2.9%), 2nd in Russian and Danish. Fewer errors than all three OpenAI real-time models in 13 of the 14 languages we publish.
AssemblyAI real-time benchmarkMethod
FLEURS: short Wikipedia sentences read aloud. Measures how many words come out wrong.
AssemblyAI published scores for 14 real-time engines. We ran Baian’s live interpreter on the same test set.
We joined clips into 15-minute recordings with 1.5-second gaps and played them into Baian’s live interpreter in real time, like a microphone, with automatic language detection. AssemblyAI streamed each clip separately with the language set in advance. Scoring ignores punctuation, capital letters, Arabic vowel marks and how numbers are written. Our charts show 13 of AssemblyAI’s 14 engines; the full table is on AssemblyAI’s site.
- Baian against professional translators (FLoRes)October 2026
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.
FLoRes-200 professional translationsMethod
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.
- Live delay13 to 15 October 2026
Median 2.1 seconds across 53 recordings in 15 languages (1.3 to 2.7 seconds per recording).
Method
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.
- How quickly words appear13 to 15 October 2026
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.
Method
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.
- European Parliament interpreters2019
Median 2.69 seconds behind the speaker, across 180 speeches.