Google releases Gemini 3.8 Flash TTS voice generation models
The models support custom voices in 100+ languages, two-speaker dialogue, nonverbal cues and voice cloning from a 30-second sample, with SynthID watermarks on all audio.
Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS turn voice generation into a dynamic creative studio. 🎙️ Design bespoke voices from scratch across 100+ languages using simple prompts 🎬 Tailor scenes line by line with natural script cues for tone, accents, and pacing 👥 Stage two-speaker dialogue from a single script with natural turn-taking 💬 Script nonverbal cues like laughs, sighs, and listening interjections 🗣️ Recreate consistent vocal profiles from a 30-second audio sample of your voice or a voice you have the rights to use 📚 Access 2,000+ production-ready voices with broad language coverage Plus, every audio clip is watermarked with SynthID, ensuring AI-generated speech remains detectable.