Google Launches Two Expressive Gemini TTS Models

Google has introduced two new text-to-speech models: Gemini 3.8 Flash TTS for creative voice design and Gemini 3.8 Flash-Lite TTS for high-volume, cost-efficient production. Both models offer granular performance control, including line-by-line direction, backchanneling, and multi-speaker scene staging across 100-plus languages. Key features include generative voice design from natural language prompts, a library of 2,000-plus production-ready voices, and voice replication from 30-second audio samples with built-in consent verification. Gemini 3.8 Flash TTS ranked first on Hume AI's Voice Design Benchmark with a score of 71.4.