Affiliate links on Android Authority may earn us a commission. Learn more.
Gemini Live's native audio model helps it speak more like a human
November 12, 2025

- Google previewed Gemini Live model updates at the Google Pixel 10 launch event, and they’re now rolling out widely for iOS and Android users.
- Gemini Live is now likely powered by Gemini 2.5 Flash Live API native audio, making for more “adaptive and expressive” chats.
- Users can personalize Gemini Live’s speech to match their preferences, changing aspects of its delivery like speed, tone, and accents.
Gemini Live is Google’s conversational AI assistant, and the company is rolling out a model update that aims to make it more natural and human-like. Google first previewed the improved experience, known as native audio output, at the Google Pixel 10 launch event. Now, it’s available to all Gemini Live users starting today following a limited rollout in October.
Google explains that Gemini Live’s new model updates “dramatically improve its ability to understand and use key elements of human speech.” This results in “more adaptive and expressive conversations,” according to the blog post. Gemini Live users can take advantage of the assistant’s better understanding of speech and language to tailor their experience. For example, users might ask Gemini Live to speed up, slow down, or adjust its tone and accent.
Don’t want to miss the best from Android Authority?
- Set us as a favorite source in Google Discover to never miss our latest exclusive reports, expert analysis, and much more.
- You can also set us as a preferred source in Google Search by clicking the button below.
The changes are rolling out following a behind-the-scenes update to Gemini Live’s core AI model. Google didn’t specify the name of the new model, but it is likely Gemini 2.5 Flash Live API native audio. This model first became available in public preview as of September 2025, shortly after the Made by Google teaser. It’s described as bringing “dramatically improved audio quality that feels like speaking with a person,” which sounds a lot like the new Gemini Live experience.
Google shared a few ways users can personalize their conversations with Gemini Live using its new capabilities. Gemini Live can adjust its speed to your preference, improving accessibility. In the example above, a student asks Gemini Live to talk faster so they can hear the answer before class starts.
Learning is a key application of Gemini Live’s natural language understanding. Google also suggests using Gemini Live to practice speaking, perhaps in a new language. It can help users prepare for a job interview or simply hone in on their public speaking skills. Finally, Gemini Live can tell stories with character accents, or pick a fun accent situationally.
When you customize a Gemini Live session, it’ll last until you end that session. Starting a new Gemini Live conversation brings everything back to the default, giving users a blank slate that can be customized again.
Gemini Live’s model updates are available now in the Gemini app for iOS and Android.
Thank you for being part of our community. Read our Comment Policy before posting.

