Google Unveils Gemini 3.8 TTS Models for Dynamic Voice Generation
Google has introduced two new text-to-speech (TTS) models as part of its Gemini family, aimed at transforming voice generation into a dynamic creative studio. The Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS models allow creators, developers, and enterprises to create richer, more expressive audio experiences.
The Gemini 3.8 Flash TTS model is built for deep creative direction and character design, enabling the creation of entirely new voices from scratch using natural language prompts. This model is ideal for gaming, immersive audiobooks, podcasts, and interactive media.
On the other hand, the Gemini 3.8 Flash-Lite TTS model is optimized for high-volume, cost-efficient scale, making it suitable for high-volume dubbing, audio content creation, and expressive voice agents with fine-grained control over tone, pacing, and expressive nuance.