Gemini 3.8 text-to-speech says hello
On September 23, 2026, Google released Gemini 3.8 Flash TTS and Flash-Lite TTS, which create custom voices from text prompts and control delivery line by line. Flash targets creative projects such as games and audiobooks; Flash-Lite suits high-volume, lower-cost uses like dubbing and voice agents.
What the article says
On September 23, 2026, Google presented two text-to-speech models. Gemini 3.8 Flash TTS is built for creative direction and character design, creating voices from natural-language descriptions across more than 100 languages and dialects. Gemini 3.8 Flash-Lite TTS targets high-volume, cost-efficient uses such as dubbing and voice agents.
Features include a library of 2,000+ voices, voice replication from a 30-second sample (with a recorded verbal consent), saved custom voices, line-by-line performance direction, long-form generation and two-speaker scenes; voice remixing is listed as coming soon. Google cites Flash TTS ranking first on Hume AI's Voice Design Benchmark (71.4). All audio carries a SynthID watermark. Flash TTS is available in the Gemini API, AI Studio and Gemini Notebook, and Flash-Lite TTS in the Gemini API, AI Studio and Google Vids; voice replication is unavailable in several regions, including the EEA and the UK.
Read the official article AnnuIA profile
Summary written by AnnuIA in its own words from the official page of Google DeepMind. The content and rights belong to the publisher: please read the original article.