GOOGLE LAUNCHES GEMINI 3.8 FLASH TTS AUDIO MODELS

The new text-to-speech models represent an advancement in Google's audio generation capabilities. Gemini 3.8 Flash TTS serves as the primary offering, while the Flash-Lite variant provides a lighter-weight alternative. With support for over 100 languages, the models expand accessibility for multilingual users and developers. Google describes the models as its most expressive to date, suggesting improvements in naturalness and tonal quality compared to previous versions. The release targets developers and enterprises building voice applications. Both TTS variants integrate with Google's broader Gemini ecosystem, enabling integration into existing AI workflows. The company has not disclosed specific pricing details or availability timelines beyond the announcement. Flash-Lite's introduction indicates Google's strategy to offer performance-efficiency tradeoffs for different use cases and computational constraints.