AI Briefing#full-duplex
The latest AI and developer news about #full-duplex, with the original source and a short summary.
The latest AI and developer news about #full-duplex, with the original source and a short summary.
The Apache-2.0 licensed model family offers three builds, with the Flash variant achieving 0.31 s first audio latency and supporting 40 concurrent users per 80 GB GPU.
The 45B parameter model processes audio, video, and text in 160ms chunks while delegating complex reasoning to a larger backend model to maintain low latency.
The model operates as a true speech-to-speech system with inference speeds faster than real-time and runs locally on MacBook Pro M4 Max or higher.
The model achieves 250 ms median endpoint latency and integrates with Gemma 4 E4B and VoxCPM2 for voice agents.
OpenAI has launched GPT-Live 1, a bidirectional voice model capable of simultaneous listening and speaking, on the AI Gateway.
OpenAI has launched GPT-Live-1 on its API, supporting latency-free full-duplex voice conversations and backend model integration.
ByteDance Seed has deployed SeedRealtime, a full-duplex model that processes audio and video in real time, on Doubao.
NVIDIA released an 11B voice model supporting 450ms response times and tool calling.
OpenAI built the architecture for GPT-Live in six months to enable real-time voice conversations.
OpenAI built a real-time, bidirectional system for natural voice conversations in GPT-Live.
Microsoft is testing MAI Realtime, a full-duplex real-time voice model, in MAI Playground.