Google has introduced two new text-to-speech models called Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS which it says are its most expressive text-to-speech audio models yet. The two models offer text-to-speech in over 100 languages. The models allow users to generate entirely original voices from scratch using natural language prompts or train the models with their voice using audio samples. The models allow creators to control a wide variety of emotional responses like laughs, sighs, pacing the speech etc.

Full report : Google has launched two new text-to-speech models called Gemini 3.8 Flash & Gemini 3.8 Flash-Lite.