ReleaseGoogle

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

Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.

March 26, 20261 min readPublished byGoogle DeepMind

Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.

Read the original source
https://deepmind.google/blog/gemini-3-1-flash-live-making-audio-ai-more-natural-and-reliable/
Tags
multimodalinference
All news

Read also

Release

DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

1 min read
Release

Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

1 min read
Release

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors

1 min read