Google DeepMind releases updated Gemini 2.5 Flash Native Audio speech model
Original title:Improved Gemini audio models for powerful voice experiences
AI summary
Google DeepMind released an updated Gemini 2.5 Flash Native Audio model for real-time voice agents, scoring 71.5% on ComplexFuncBench Audio and raising developer instruction-following rates from 84% to 90%. It is available in Google AI Studio and Vertex AI and is rolling out in Gemini Live and Search Live.
Key Takeaways
- Google DeepMind released an updated Gemini 2.
- 5 Flash Native Audio model for real-time voice agents,scoring 71.
- 5% on ComplexFuncBench Audio and raising developer instruction-following rates from 84% to 90%.
- It is available in Google AI Studio and Vertex AI and is rolling out in Gemini Live and Search Live.
Quick Facts
- Published
- Updated
- Source
- Google DeepMind:Blog(RSS)
- Category
- Model Releases
- AI score
- 68
原文给出具体评测分数和功能细节,读者可以据此评估新模型在语音智能体和翻译场景的可用性。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Google DeepMind releases updated Gemini 2.5 Flash Native Audio speech model. December 13, 2025. https://new.nat6.net/en/news/iw88ze1rlsc2dgt3gl7cqo9bx/