Voice assistants often fall silent when a request gets complicated. Google launched Gemini 3.8 Live Extended Thinking on Sept. 15 to keep the conversation going while the model reasons through multistep tasks and runs tools in the background.
The model arrived alongside the lower-latency Gemini 3.8 Live. For developers, Extended Thinking changes a basic assumption of voice-agent design: the end of a spoken response no longer necessarily means the underlying task is finished.
Both models are generally available through the Gemini API and Google AI Studio, according to Google’s Gemini API release notes. They join Google’s expanding Gemini model…
Read the full article at TECHREPUBLIC.COM
