Gemini 3.8 text-to-speech says hello

Google has introduced two new text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, to its Gemini Audio family. These models allow users to create and customize realistic voices with options for accent and emotional tone, making them ideal for creating audiobooks, games, or podcasts that sound like real people speaking.

Google has also implemented safety measures to ensure responsible use of these synthetic voices. The models provide developers with precise control over how each line is delivered, securing top spots on Hume AI's Voice Design Benchmark and Quality Index. With support for over 100 languages, these models enable creators, developers, and enterprises to build high-quality, multilingual voice experiences worldwide. They are now available in Google AI Studio for developers to utilize in their applications.