Google launches Gemini 3.8 Flash TTS voice models

Google has launched two new Gemini 3.8 Flash TTS voice models designed for performance scripting and audio production. The models target different tasks, with Gemini 3.8 Flash TTS aimed at interactive entertainment and game development, while Gemini 3.8 Flash-Lite TTS focuses on automated dubbing and conversational agents. The new models offer over 2,000 pre-built vocal profiles, allowing for extensive linguistic diversity, including Quebec French and Mexican Spanish. Performance improvements have been validated through Hume AI benchmarks, where Gemini 3.8 Flash TTS achieved top scores in audio quality assessments.