AIMarkTechPostabout 3 hours ago
OpenAI Ships Two New Realtime Voice Models
10 min read
OpenAI released gpt-realtime-2.1 and gpt-realtime-2.1-mini in its API for low-latency voice agents. The mini model is a reasoning model for realtime voice at the same cost as gpt-realtime-mini. OpenAI also cut p95 latency by at least 25% across Realtime voice models through improved caching.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
