Search
On September 23, 2026, Google introduced two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, upgrading voice generation from static presets to dynamic creative tools. Gemini 3.8 Flash TTS is designed for in-depth creativity and character design, enabling the creation of entirely new voices through natural language prompts, suitable for scenarios such as gaming and audiobooks. Gemini 3.8 Flash-Lite TTS, on the other hand, targets high-volume, cost-effective scenarios, optimizing voiceover and audio creation. Both models support over 100 languages, feature capabilities such as voice cloning, mixing, and dual-voice orchestration, and incorporate built-in safeguards to ensure content traceability and respect for identity.
-
C114 Communication Network -
Communication Home
