Tag
LiveKit Agents is an open-source real-time voice agent framework supporting WebRTC, telephony integration, semantic turn detection, MCP tool calling, and multi-agent handoff, helping developers quickly build real-time voice applications such as AI customer service and phone bots.
The author shares Parlor v2, a fully local GPT-Live clone running on an M3 Pro, built as a cascade system after failed attempts to fine-tune Gemma 4 12B for full-duplex behavior.
TEN is a framework for building real-time multimodal conversational AI agents, offering configurable STT, LLM, and TTS components, a visual designer, and deployment options including self-hosting and split deployment.
This paper evaluates four leading real-time voice AI systems (GPT Realtime 2, Gemini 3.1 Flash Live, Qwen3.5 Omni Plus, Omni Flash) and finds they consistently act on words rather than vocal tone, ignoring distress, fear, or sarcasm even when they can perceive them—termed the 'emotional intelligence gap' of voice AI.
This article shares hard-won lessons from building real-time voice AI agents, highlighting the importance of proper turn-taking, VAD handling, billing awareness, and avoiding echo loops.
A community discussion asking what people are using for AI voice agents in production, focusing on latency, interruption handling, and reliability, with mentions of LuMay Voice Agent, Vapi, Retell, and Twilio.
OpenAI has launched GPT-Realtime-2, integrating GPT-5-level reasoning into the real-time voice API, enabling voice assistants to think and solve problems in real time during conversations.