AssemblyAI Launches STT-3.7 Transcription Models for Real-World Audio

AssemblyAI released three STT-3.7 transcription models split by use case, cutting latency in half for voice agents and improving accuracy on noisy, real-world audio, alongside its first TTS model and a rewritten inference engine.

2026-11-18 ~ 2026-11-19 · 3 related posts