AssemblyAI Launches Universal-3.5 Real-Time Transcription

ArtificialAnlys · x · 2026-07-06

AssemblyAI has released Universal-3.5 Pro Realtime, an upgrade from Universal-3 Pro Realtime. The streaming speech-to-text model achieves 4.1% WER on AA-WER Streaming, delivering final results for the first sentence in about 0.4 seconds. It allows context injection at the start of a call and after each agent dialogue turn without requiring a reconnection. It offers three modes: Balanced, Max Accuracy, and Min Latency.

Related event: AssemblyAI Launches Universal-3.5 Speech Models(4 posts)→

Original post →

More from Multimodal

Multimodal channel →