Gemini TTS lets developers design and direct voices by prompt
Developers can now build custom voices from natural-language prompts and direct every line's acting, pacing, dialect, and delivery, instead of choosing from static presets. Gemini 3.8 Flash TTS targets character and creative work, while Flash-Lite is tuned for high-volume dubbing and voice agents. Google says Flash TTS supports more than 100 languages and dialects, plus voice replication from a 30-second sample with consent checks, SynthID watermarking, and C2PA credentials.