Tag
5 articles
This article explains full-duplex speech processing and how Block's Dessa model represents a breakthrough in real-time conversational AI through exclusive human conversation training and local deployment capabilities.
Learn how Alibaba's new Qwen-Audio-3.1-Realtime AI model enables natural, full-duplex voice conversations by listening, thinking, and deciding when to speak.
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.
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.
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.