PulseAugur
EN
LIVE 04:51:26

AssemblyAI launches Universal-3.5 Pro with expanded multilingual transcription

AssemblyAI has released its Universal-3.5 Pro model, enhancing its multilingual transcription capabilities. This new model supports automatic language detection and native code-switching across 18 languages, a significant increase from its previous generation. The model can transcribe audio in over 99 languages by falling back to Universal-2 for those not explicitly supported for code-switching, offering improved accuracy and a more seamless experience for handling diverse linguistic content in a single API call. AI

IMPACT Enhances handling of code-switching in transcription, potentially improving accuracy for global communication tools.

RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on AssemblyAI blog →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AssemblyAI launches Universal-3.5 Pro with expanded multilingual transcription

COVERAGE [1]

  1. AssemblyAI blog TIER_1 English(EN) ·

    Multilingual transcription: How to detect, diarize, and transcribe audio across languages

    Detect the language automatically, diarize across languages, and handle code-switching in one API — 99+ languages, 18 with native code-switching.