Google is enhancing Gemini's text-to-speech (TTS). On Tuesday at Google I/O 2025, the company previewed a new TTS feature, built on native audio output, that can "converse in more expressive ways."
Google’s Tulsee Doshi showed a quick demo of the Gemini 2.5 TTS models onstage in Mountain View. It showed an AI-powered voice that sounds more natural and less robotic, with subtler nuances.
The TTS can converse in over 24 languages, switching between them seamlessly. The demo showed the model beginning in English, shifting to Hindi, and then circling back to English. They all used the same voice, helping create the illusion that it’s the same “person.” The TTS can also switch to a whisper (which sounded a little creepy) on the fly.
The new text-to-speech is available starting today in the Gemini API. Also on Tuesday, the Gemini Live API will have a 2.5 Flash preview of native audio dialog.
Google's annual I/O developer conference kicked off on Tuesday, May 20. Google is highlighting new and notable improvements to its Gemini AI services, including real-time translation, AI enhancements to Project Astra computer vision and more. Follow Engadget's Google I/O liveblog for real-time coverage of the event. Google previewed some key pre-I/O Android 16 news during its Android Show video stream last week.
This article originally appeared on Engadget at https://www.engadget.com/ai/googles-new-text-to-speech-can-switch-languages-on-the-fly-174528459.html?src=rss