Google has introduced a new text-to-speech model, Gemini‑TTS, in the Gemini 3.1 series, which the company calls its "most expressive text-to-speech solution." This model can generate natural, high-fidelity speech, and developers can also control the emotion, rhythm, and style of the speech through prompts, such as precisely adjusting tone, pauses, and emotions in narration or dialogue.
