Google launches two new text-to-speech models with extensive voice libraries and cloning capabilities. The release includes gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, featuring over 2,000 built-in voices and support for custom voice creation from a thirty-second audio sample. Developers can access these capabilities via the Gemini API to build multi-speaker conversational audio applications.
Opening Kapyn…