Google DeepMind·· 2025-12-13PicksAI score62
Google Releases Upgraded Gemini 2.5 Flash Native Audio with Real-Time Voice Translation
Improved Gemini audio models for powerful voice experiences
AI briefing
Google releases the upgraded Gemini 2.5 Flash Native Audio, designed for real-time voice agents. It improves complex workflow handling, instruction following, and multi-turn dialogue capabilities, leading on ComplexFuncBench Audio with 71.5%, and raising developer instruction-following rates from 84% to 90%.
Why it matters
Gemini 2.5 Flash Native Audio updates function calling, instruction following, and multi-turn dialogue capabilities, and adds real-time voice translation, enabling evaluation of usability in voice agent and translation scenarios.
Open original deepmind.google