Vamsi Batchu(@vamsibatchuk):Introducing Gemini 3.8 Flash TTS and Flash-Lite TTS from 🗣️🎙️ . Our most expressive audio generation models yet !!! here are some of the awesome capabilities from these models.. 🏆 #1 Hume Voice Design (71.4) and accent modeling (60.8) 🎨 Design unique voices from scratch with natural language prompts 🌍 100+ languages and dialects, including regional accents 📚 2,000+ production-ready voices in the library ⏱️ Voice replication from a 30-second sample with consent checks 🎬 Line-by-line direction for pacing, emotion, laughs, and pauses 👥 Native two-speaker scene staging from one script 📖 Hours of long-form audio with minimal speaker drift & much more...

2026.09.23 15:33

Introducing Gemini 3.8 Flash TTS and Flash-Lite TTS from 🗣️🎙️ . Our most expressive audio generation models yet !!! here are some of the awesome capabilities from these models.. 🏆 #1# Hume Voice Design (71.4) and accent modeling (60.8) 🎨 Design unique voices from scratch with natural language prompts 🌍 100+ languages and dialects, including regional accents 📚 2,000+ production-ready voices in the library ⏱️ Voice replication from a 30-second sample with consent checks 🎬 Line-by-line direction for pacing, emotion, laughs, and pauses 👥 Native two-speaker scene staging from one script 📖 Hours of long-form audio with minimal speaker drift & much more...