Google has released two new text-to-speech (TTS) models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, which it calls its most expressive audio generation models yet. The models are available for developers and creators through the Gemini API and Google AI Studio, and are designed to produce more natural, human-like speech with greater control over tone and nuance.
The primary model, Gemini 3.8 Flash TTS, allows for creating custom voices and characters from text prompts and supports over 100 languages and dialects. The 'Lite' version is optimized for high-volume and cost-efficient applications like dubbing and voice agents. The release aims to enhance creative applications in gaming, audiobooks, and interactive media, keeping Google competitive in the generative AI space.