🎤 OpenAI reveals the secret behind GPT-Live’s natural voice conversations

🎤 OpenAI reveals the secret behind GPT-Live’s natural voice conversations OpenAI has shared how GPT-Live delivers conversations that feel surprisingly human. Instead of waiting for you to stop talking, GPT-Live uses continuous audio, meaning it listens and speaks at the same time for a smoother, more natural flow. Complex reasoning and tool calls happen in the background while a faster model keeps the conversation going, so you don’t experience awkward pauses. OpenAI also rebuilt much of its voice infrastructure in Go, significantly reducing latency. The company says the new system’s slowest responses are now as fast as the average responses from the previous version. For long conversations, GPT-Live quietly switches to a new model that’s already loaded with your chat history, keeping the conversation going without interruptions. It also introduced WARP (WebRTC Abridged Roundtrip Protocol), cutting connection setup from six network round trips to just one, with Instant Connect allowing sessions to start from a single UDP packet. The result? A voice assistant that feels far more like talking to a real person. @aipost 🏴