Google launched Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS on September 23, adding a higher-expression speech model alongside a lower-cost option for high-volume audio work.
In the Google announcement, the company says Flash is aimed at more directed voice production, while Flash-Lite is built for throughput-sensitive workloads. Flash supports prompt-based voice design across more than 100 languages and dialects, and Google says builders can also use a library of more than 2,000 preset voices.
Google is also gating voice replication: cloning requires a 30-second sample plus a matching spoken consent recording from the voice owner. The models also support line-by-line delivery control, long-form generation and two-speaker scenes. Rollout began in Google AI Studio and the Gemini API on September 23, though voice replication is unavailable in the EEA, UK, Switzerland, India, Illinois and Texas.