Google Launches New Models for Dubbing, ‘Creative’ Voices

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS support more than 100 languages and provide access to more than 2,000 production-ready voices.

Google describes Gemini 3.8 Flash TTS as its new “flagship creative” speech model and the higher-fidelity option of the two. Supporting 130 languages, it is designed for audiobooks, studio narration, games, podcasts, complex multi-speaker dialogue, and other applications requiring nuanced acting and detailed performance control. Google highlights its handling of difficult pronunciations and regional and minority dialects. According to the company, the model can maintain voice identity and quality across extended dialogue and long-form narration.

The future of AI adoption depends on trust, ethics and human expertise.

Partner spotlight Fast isn't good enough. A resource to help identify how to leverage AI and scale globally.