Google Launches Gemini 3.8 Flash TTS Models with Custom Voice Design and 100+ Language Support

Google has introduced two new text-to-speech models under the Gemini 3.8 family: Gemini 3.8 Flash TTS, built for deep creative direction and character voice design, and Gemini 3.8 Flash-Lite TTS, optimized for high-volume, cost-efficient audio production. Both models are available across Google AI Studio, the Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids, and support more than 100 languages and dialects.

The Flash TTS model allows creators to generate entirely original character voices from natural language prompts, with line-by-line control over acting cues, pacing, dialect, and emotional tone — targeting use cases such as gaming, audiobooks, podcasts, and interactive media. The Flash-Lite variant is aimed at high-volume workflows like dubbing and voice agent deployment. Both models ship with safety features including audio watermarking, and voice replication from a 30-second sample is supported for users with appropriate rights.