Skip to content

Recorded subtitles · Accuracy

Subtitle accuracy, in plain numbers.

How Baian’s caption tool compares with professional translators and with other AI.

Recorded speech
Baian transcribes the audio, then translates it.
Professional translations
The translators worked from the written sentences.

01 · Against translators

They read the text. Baian only heard it.

Even with speech recognition as an extra step, Baian scored above the professional translations in Hausa, Tamil, Swahili and Urdu. The judge found no clear difference in 21 other languages.

Professional translatorsRead the text
BaianHeard the audio

Baian’s subtitles were preferred:

  • Hausa75%preferred
  • Tamil69%preferred
  • Swahili68%preferred
  • Urdu67%preferred

The line marks 50%: an even split.

Sources and methods

02 · Against an edited translation

Preferred 68% of the time.

On the WMT26 test, Baian was preferred over the professionally edited translation on 91 of 133 clips.

English to Egyptian Arabic

  • Baian preferred68%preferred

The line marks 50%: an even split.

03 · Against other AI

First in five languages.

Out of 15 or 16 engines in each language.

Recorded speech: transcription rankingsErrors in words, or characters for Korean and Japanese. Lower is better.

  • SpanishRecorded

    Baian3.3%1st
    OpenAI4.3%2nd

  • RussianRecorded

    Baian4.7%1st
    Google Gemini 2.5 Flash6.4%2nd

  • HindiRecorded

    Baian1stRank only

  • FrenchRecorded

    Baian4.3%Joint 1st
    AssemblyAI4.6%Joint 1st

  • JapaneseRecorded

    Baian2.51%Joint 1st
    ElevenLabs2.52%Joint 1st
These scores measure transcription, not the finished translation. Sources and methods

Your recording. More languages.

Upload a recording, choose your languages and download the subtitles.

Upload a recording
Sources and methodsEvery number on this page, with its test and date
  • Saudi Arabic mixed with English (Perle)Paper May 2026; Baian runs October 2026

    Caption Tool 9.5% of words wrong, Baian’s live interpreter 15.6%, ElevenLabs 21.3%, OpenAI 43.7%, Azure 50.6%, Google 62.4%.

    Perle, May 2026 (arXiv)
    Method

    300 recordings of Saudi speakers switching between Arabic and English. Measures words wrong and meaning kept.

    Perle’s authors tested ElevenLabs, OpenAI, Microsoft Azure and Google. We ran both Baian products on the same recordings.

    Scored with Perle’s own rules and meaning model. The Caption Tool ran in transcription-only mode; Live used default settings with no language hint.

  • Recorded speech recognition (Verli)Verli July 2026; Baian October 2026

    1st in Spanish, Russian and Hindi; joint 1st in French and Japanese.

    Verli speech-to-text accuracy, July 2026
    Method

    200 FLEURS sentences per language. Measures words wrong.

    Verli tested 15 or 16 engines per language. We ran Baian’s caption tool on the same test set.

    Verli tested each engine as it was in July 2026 on its own 200-sentence FLEURS sample. We used the same test set and scoring rule on a different 200 sentences. Verli’s scoring rule splits Hindi words at vowel signs, which roughly halves everyone’s error rate, so we publish Hindi as a rank only.

  • 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 translations
    Method

    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.

  • English speech to Egyptian Arabic (WMT26)15 October 2026

    2nd of 30 systems, and preferred over the professional post-edited translation on 91 of 133 clips (68%).

    WMT26 general translation test
    Method

    133 English YouTube clips, the speech test from the 2026 Conference on Machine Translation.

    Baian scored every published system’s output, and its own, with Google’s MetricX-24 automatic judge.

    Baian received the same automatic transcript as the other systems. WMT’s own human raters rank systems differently, so we always describe this as an automatic score.

  • Urdu speech recognition (Qwen3.5-Omni paper)Paper April 2026; Baian October 2026

    13.2% of words wrong, the lowest in the comparison. OpenAI GPT-4o Transcribe got 19.7%.

    Qwen3.5-Omni paper, April 2026 (arXiv)
    Method

    FLEURS Urdu recordings. Measures words wrong.

    The Qwen3.5-Omni authors published scores for several systems; we ran the Caption Tool on the same test set.

    Scored with the standard Whisper rule: lower case, punctuation removed.