OpenAI publishes engineering deep-dive on delivering low-latency voice AI at scale

OpenAI published an engineering post on how it delivers real-time voice AI globally — covering streaming pipelines, latency budgets, and infrastructure tradeoffs. The post drew strong developer interest with 385 points and 120 comments on Hacker News and lands as xAI ships emotion-aware Custom Voices on Grok and Apple is rumored to pivot Siri to Gemini.