kapynBig Tech

Gemini 3.8 text-to-speech says hello

Gemini 3.8 adds text-to-speech capability. Google’s Gemini 3.8 now generates spoken audio from text, enabling developers to embed voice output directly in their applications. The feature uses advanced neural synthesis and is accessible through the Gemini API, expanding the model’s multimodal toolkit.

Google DeepMind·Sep 23, 2026

Opening Kapyn…