Sesame Releases TurnBench for Real-Time Conversational Turn-Taking

shinjiw_at_cmu · x · 2026-08-29

Sesame released TurnBench, a multi-domain benchmark for evaluating "when to speak and when to yield" in real-time conversations. It features a 30-hour dual-channel corpus with hand-annotated end-of-turn and interruption events. The leaderboard ranks models by recall, FPR, and latency; Voice Activity Projection leads with 0.845 recall, while OpenAI Realtime (Semantic VAD) scores 0.303. The training set, otoSpeech, is available on Hugging Face.

Related event: Sesame Releases TurnBench for Evaluating Voice AI Turn-Taking(2 posts)→

Original post →

More from Research

Research channel →