{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/a7caaffbc3234acfb93a7e0093ff579b\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/a7caaffbc3234acfb93a7e0093ff579b-c35b8d9a7747bd82.gif","duration":80.758,"title":"NesterConversationalBot Demo","description":"This demo showcases NesterConversationalBot, NesterLabs’ open-source, ultra–low-latency voice assistant that fuses Speech-to-Text (Deepgram), Retrieval-Augmented Generation (RAG), LLM function calling (Google / OpenAI), and Text-to-Speech (ElevenLabs). You’ll see real-time audio streaming over WebSockets, Hinglish support, live latency metrics, and how tools (like a RAG retriever) are invoked intelligently to keep the system both fast and factual."}