Gemini 3.8 text-to-speech

	Gemini 3.8 text-to-speech(blog.google)
	328 points by swolpers 20 days ago \| 147 comments
	tl;dr: Google released Gemini 3.8 Flash TTS and Flash-Lite TTS, text-to-speech models supporting 100+ languages with generative voice design from natural language prompts, a 2,000+ voice library, and 30-second voice cloning with consent verification and SynthID watermarking. The models offer line-by-line performance direction, two-speaker scene staging, and non-verbal cues like laughs and sighs, topping Hume AI's Voice Design Benchmark and Voice Arena preference tests. Available now via Gemini API, Google AI Studio, Gemini Notebook, and Google Vids, with enterprise access coming soon.
	HN Discussion: ↓Google's rollout is inconsistent and sloppy across platforms with unclear pricing and errors ↓Voice cloning consent and data storage raises privacy concerns ↑The expressive control and voice library is useful for creative audiobook/fanfic projects ↑Sharing personal experiments and playground tools built on the new model •Asking about alternatives, particularly local/open-source TTS options