Tag

#full-duplex

3 articles

OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time

OpenAI releases GPT-Live-1 API, enabling developers to build apps with real-time, full-duplex voice interaction. The API scores 80.1% in interactivity tests, though it comes at a cost of $0.05 per minute.

Sep 1025

ByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Model

Explore the technical innovations behind ByteDance's SeedRealtime, a multimodal AI model that processes audio, video, and text in real time for more natural human-AI interaction.

Aug 995

OpenAI Releases GPT-Live and GPT-Live-1 mini: Full-Duplex Voice Models That Delegate Deeper Reasoning to GPT-5.5

This article explains OpenAI's new GPT-Live voice models that use full-duplex architecture and delegate complex reasoning to GPT-5.5, demonstrating advanced AI system design principles.

Jul 874