VoiceMem Cuts Voice AI Memory Retrieval Latency to 134ms

Researchers from NTU and other top universities released VoiceMem, a streaming dual-brain memory framework for real-time voice agents that cuts memory retrieval latency to 134ms. Code and paper are publicly available.

2026-09-07 ~ 2026-09-07 · 2 related posts

• VoiceMem: dual-brain memory brings near-zero latency long-term recall to voice agents — 青稞AI · 2026-09-07
• VoiceMem: A Dual-Brain Memory System Cuts Voice AI Retrieval to 134ms — 机器之心 · 2026-09-07