Build stronger customer experience outcomes with voice, text, and speech AI
From Google Cloud · · 1 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.
If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.
Description
Delivering natural, low-latency voice and digital customer service often forces teams to stitch together separate speech, reasoning, and text-to-speech models. The Gemini Composite V1 model removes that operational burden. Built with Google DeepMind, it coordinates specialized Listener, Thinker, and Talker capabilities to cut latency by 50%, filter out background noise, and follow strict enterprise policies across voice, chat, and messaging. Watch to learn how you can define your agent logic once while Google manages the underlying model for a human-grade customer experience.