Live interpretation · Accuracy
Live accuracy, in plain numbers.
Compare Baian with professional interpreters, written translations and other AI.
How does the translation compare?Translation follows in about 2.4 seconds.Seconds behind the speaker. Lower is better.
Against translators
They had the text. Baian worked live.
Baian was preferred on most sentences in Arabic, Hindi and Korean. The test found no clear difference in overall quality.
How often Baian was preferred
- Arabic58%preferred
- Hindi65.5%preferred
- Korean61.5%preferred
The line marks 50%: an even split.
Against other AI
First in live Arabic and Korean.
Speech recognition results on AssemblyAI’s real-time benchmark.
Live speech: transcription rankingsErrors in words, or characters for Korean and Japanese. Lower is better.
-
ArabicLive
Baian5.1%1stSpeechmatics Enhanced6.5%2nd -
KoreanLive
Baian2.9%1stGoogle Gemini 3.5 Live3.8%2nd -
RussianLive
Google Gemini 3.5 Live5.3%1stBaian6.4%2nd -
DanishLive
Google Gemini 3.5 Live9.1%1stBaian9.9%2nd
All Arabic transcription results
| System | 016% | Result |
|---|---|---|
| Baian | 5.1% | |
| Speechmatics Enhanced | 6.5% | |
| Google Gemini 3.5 Live | 6.7% | |
| Speechmatics Standard | 8.4% | |
| Amazon (AWS) | 8.5% | |
| Meta Muse | 8.9% | |
| OpenAI GPT-4o Transcribe | 9.4% | |
| OpenAI GPT Realtime | 10.5% | |
| ElevenLabs Scribe v2 | 10.8% | |
| OpenAI GPT-4o mini Transcribe | 11.7% | |
| AssemblyAI Universal | 12.1% | |
| Microsoft Azure | 12.5% | |
| Gladia | 15.1% |
Questions
Questions about live accuracy.
How fast is Baian’s live interpreter?
Our estimates are about 1 second for original-language captions and 2.4 seconds for the first translated text. These measurements are to the captured feed, not a phone screen or the listener’s headphones. Previews can change as the speaker continues.
How accurate is the live translation?
Google’s automatic judge preferred Baian on 58% of sentences in Arabic, 65.5% in Hindi and 61.5% in Korean. Overall quality was about the same: there was no clear statistical difference from the professional translations. Baian worked live from audio; the translators had the text.
How does it compare with other AI?
On AssemblyAI’s real-time speech benchmark, Baian ranked first for live Arabic and Korean, ahead of OpenAI, Google and ElevenLabs.
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 demoSources 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.