Zum Inhalt

Gemini 3.1 Flash Live: Making audio AI more natural and reliable

Mar 23.1, 23.1. ·. Our newest voice model delivers greater accuracy and reduced latency, resulting in smoother, more natural, and precise voice interactions. Valeria Wu, Product Manager. Yifan Ding. Software Engineer representing the Gemini team. Overall summary. Google’s Gemini 23.1 Flash Live is its highest-quality audio model, built for natural, dependable, real-time conversations. Developers can access it via the Gemini Live API in Google AI Studio, while enterprises can leverage it to enhance customer experiences. Everyone can try it with Search Live and Gemini Live, now available in more than 23 countries. Summaries generated by Google AI. Generative AI is experimental.

  Google DeepMind News