{"slug": "boson-ai-introduces-a-45b-model-that-talks-and-renders-a-face", "title": "Boson AI introduces a 45B model that talks and renders a face", "summary": "Boson AI, the Santa Clara company co-founded and led by Alex Smola, introduced Higgs Realtime Duplex on November 5th, 2026, describing it as its first full-duplex interactive omni model, built on a 45B front model. Boson AI says the model listens, watches and talks simultaneously while rendering a face, processes voice and video in 160 ms chunks, and calls tools or delegates harder questions to a larger backend model without pausing the conversation. Boson AI targets a cost of at most one-tenth of an hour of a person's time for an hour with the 45B front model.", "body_md": "# Boson AI introduces a 45B model that talks and renders a face\n\n**Alex Smola's Santa Clara company says Higgs Realtime Duplex processes voice and video in 160 ms chunks while handling tools and delegating harder questions.**\n\n        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)\n        · Published \n\nPrimary source: [Aligned News — AI Intelligence](https://x.com/rdesh26/status/2118684296441442347)\n\n## Why it matters\n\nFull-duplex interaction could let a voice agent listen while speaking, watch a screen, call tools and hand hard problems to a bigger backend model without dead air. Boson AI's target is for an hour with its 45B front model to cost at most one-tenth as much as an hour of a person's time.\n\nBoson AI, co-founded and led by [Alex Smola](https://x.com/smolix?ref=runtimewire), introduced [Higgs Realtime Duplex](https://www.boson.ai/blog/higgs-realtime-duplex?ref=runtimewire) on November 5th, 2026, describing it as the next generation of Higgs Realtime and its first full-duplex interactive omni model. The model listens, watches and talks at the same time while rendering a face of its own, according to Boson AI. It also thinks, calls tools and delegates work to a larger model without pausing the conversation, Boson AI says.…\n\nWhen you purchase through links in our articles, [we may earn a small commission](https://runtimewire.com/affiliate-monetization-standards). This doesn’t affect our editorial independence.", "url": "https://wpnews.pro/news/boson-ai-introduces-a-45b-model-that-talks-and-renders-a-face", "canonical_source": "https://runtimewire.com/article/boson-higgs-realtime-duplex-45b-voice-face-model", "published_at": "2026-11-06 16:26:02+00:00", "updated_at": "2026-11-06 19:51:19.277341+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-agents", "ai-products"], "entities": ["Boson AI", "Higgs Realtime Duplex", "Alex Smola", "Higgs Realtime"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/boson-ai-introduces-a-45b-model-that-talks-and-renders-a-face", "markdown": "https://wpnews.pro/news/boson-ai-introduces-a-45b-model-that-talks-and-renders-a-face.md", "text": "https://wpnews.pro/news/boson-ai-introduces-a-45b-model-that-talks-and-renders-a-face.txt", "jsonld": "https://wpnews.pro/news/boson-ai-introduces-a-45b-model-that-talks-and-renders-a-face.jsonld"}}