news
Gemini 3.1 Flash Live: Making audio AI more natural and reliable
March 26, 2026
Gemini 3.1 Flash Live is the latest voice model, designed to improve precision and lower latency for more fluid, natural voice interactions. The notable change is that reduced latency and higher precision should make audio AI responses feel more reliable and conversational in real time.
Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.
Source: deepmind.google