tech π€ Google drops Gemini 3.8 Flash TTS voice models
Google has launched two new Gemini 3.8 Flash TTS voice models for high-volume audio production. These systems are for interactive entertainment and automated media dubbing, released to expand Google's audio roster. The models replace 30 legacy voices, offering over 2,000 profiles in 100+ languages as of now. Developers can use these for multi-speaker staging and insert non-verbal acoustic markers into scripts. Access is available via Google AI Studio and the Gemini API for various commercial integrations. π€