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

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.”

Also read: Google says reports of ads coming to the Gemini app in 2026 are inaccurate.
The post Google Rolls Out Gemini 2.5 Flash Native Audio for Natural Voice Interactions appeared first on eWEEK.