Google's new text-to-speech can switch languages on the fly

image via Engadget

May 20, 2025, 5:45 PM

• •Google is enhancing Gemini's text-to-speech (TTS) capabilities.
• •The new TTS feature, built on native audio output, can "converse in more expressive ways."
• •The TTS can converse in over 24 languages and switch between them seamlessly.
• •The new text-to-speech is available starting today in the Gemini API.
• •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 unveiled advancements to its Gemini AI services, particularly its text-to-speech (TTS) capabilities, at the Google I/O 2025 conference. The new TTS, built on native audio output, promises more expressive and natural-sounding AI voices that can converse in over 24 languages. A demo showed the model seamlessly switching between languages and even using a whisper. The improved TTS and a preview of native audio dialog are available in the Gemini API and Gemini Live API, respectively.

Read original article