Google Rolls Out Gemini 2.5 Flash Native Audio for Natural Voice Interactions

Dec 16, 2025
2 minute read
Google Gemini Audio official logo

Image: Google

eWeek のコンテンツおよび製品のおすすめは、編集上の独立性を保っています。パートナーへのリンクをクリックすると、当社が報酬を得る場合があります。 詳細を見る

Google is turning up the volume on Gemini. This week, the company rolled out an upgraded version of Gemini 2.5 Flash Native Audio, introducing smoother conversations, improved instruction handling, and live speech translation to a broader range of users and products.

The updated Gemini 2.5 Flash Native Audio is designed for live voice interactions, especially for AI agents that talk back in real time. The new version is already available in Google AI Studio and Vertex AI for developers. 

It is also rolling out across consumer products, including Gemini Live and Search Live, where users can now talk to Google’s AI more naturally.

More natural conversations

According to Google, the update improves Gemini’s ability to handle complex, back-and-forth discussions. The model can now better remember context from earlier parts of a conversation, follow detailed instructions more accurately, and pull in real-time information without interrupting the flow of speech.

Google highlighted three major improvements:

  • More reliable function calling during conversations
  • Stronger instruction-following, with a reported 90% adherence rate
  • Better multi-turn memory for smoother, more connected chats

These changes are meant to help power live voice agents, including customer support bots and real-time assistants.

Live speech translation comes to headphones

Alongside the audio upgrade, Google is introducing live speech-to-speech translation powered by Gemini. The feature allows real-time translation through headphones, while keeping the speaker’s tone, pacing, and pitch intact.

The beta feature is launching inside the Google Translate app, starting on Android devices in the US, Mexico, and India, with iOS support and more regions planned later. The system supports over 70 languages and can automatically detect and switch between languages during two-way conversations, even in noisy environments.

As more people begin using the new audio features, the company says it will continue to improve them, promising to “continue to iterate on this experience.” Google also confirmed that the expansion will reach “more Google products, including the Gemini API, in 2026.”

Advertisement

Also read: Google says reports of ads coming to the Gemini app in 2026 are inaccurate.

Aminu Abdullahi

Aminu Abdullahi

Content Writer

Aminu Abdullahi is a B2C and B2B technology and finance writer with more than six years of experience covering enterprise IT, cybersecurity, cloud computing, artificial intelligence, fintech, business software, and emerging technologies. His work has appeared in publications including TechRepublic, eWEEK, Channel Insider, Geekflare, Enterprise Networking Planet, eSecurity Planet, CIO Insight, and Webopedia. With a technical background in computer science, he specializes in translating complex technology topics into clear, accessible content for business leaders and decision-makers.

eWeek Logo

eWeek has the latest technology news and analysis, buying guides, and product reviews for IT professionals and technology buyers. The site's focus is on innovative solutions and covering in-depth technical content. eWeek stays on the cutting edge of technology news and IT trends through interviews and expert analysis. Gain insight from top innovators and thought leaders in the fields of IT, business, enterprise software, startups, and more.

TechnologyAdvice が所有・運営しています。 © 2026 TechnologyAdvice. 無断転載を禁じます

広告主に関する開示:このサイトに掲載されている製品の一部は、TechnologyAdvice が報酬を受け取っている企業のものです。この報酬は、製品がこのサイトのどこにどのように表示されるか(表示される順序など)に影響する場合があります。TechnologyAdvice は、市場で入手可能なすべての企業やすべての種類の製品を掲載しているわけではありません。