Google introduces Gemini 3.8 Flash TTS and Flash-Lite TTS

Google announced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS on September 23, 2026, extending the Gemini 3.8 family into text-to-speech. Flash TTS is aimed at creative voice design and character performance, with natural-language voice prompts and line-by-line controls for delivery. Flash-Lite TTS is positioned for cost-efficient, high-volume work such as dubbing, audio production, and voice agents.

Flash TTS can generate custom voices across more than 100 languages and dialects, and Google says its production-ready voice library contains more than 2,000 voices. The models support directed delivery, while Flash TTS also offers two-speaker scene staging and long-form generation for formats such as audiobooks, podcasts, games, and interactive media.

Google says voice replication can use a 30-second sample, but requires a verbal consent recording from the voice owner. It also says generated audio is watermarked with SynthID. Both models are rolling out to developers through the Gemini API and Google AI Studio; Flash TTS is also rolling out to Gemini Notebook, while Flash-Lite TTS is rolling out to Google Vids. API access through Gemini Enterprise is described as coming soon.

The launch follows Google’s September 2 introduction of Gemini 3.8 Flash and Flash Cyber. Google positioned Flash for software engineering, agentic tasks, and multi-step reasoning; the new TTS variants extend the same model family into audio creation, with separate offerings for detailed creative direction and scaled production.