Google Debuts Advanced Text-to-Speech Models with Voice Cloning Capability
Google has released Gemini 3.8 Flash TTS models that bring advanced features to text-to-speech technology, including voice cloning and multilingual support.
The new models cater to a range of use cases, such as creating expressive audiobooks or optimizing high-volume tasks like dubbing and voice agents.
Flash TTS emphasizes rich, expressive outputs suitable for storytelling and gaming, while Flash Light TTS is designed for efficiency in large-scale applications.