Google's real-time multimodal API for building low-latency conversational experiences with Gemini models.
Recent stories
2 linked stories
releaseSECONDARY2026-07-30
Google ships Gemini Robotics 2 for whole-body robot control
Google released Gemini Robotics 2, ER 2, and On-Device 2 for humanoid control, embodied reasoning, and on-device adaptation. Demos showed sub-second streaming and multi-robot task handoffs.
releasePRIMARY2026-06-09
Google launches Gemini 3.5 Live Translate for 70+ languages
Google released Gemini 3.5 Live Translate for low-latency speech translation across 70+ languages in the Gemini Live API, AI Studio, and Google Translate. The same model is also heading to Google Meet in private preview for Workspace customers.