Gemini 3.1 Flash TTS

You can steer how the model speaks by dropping tags right into the text:

"[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?"

70+ languages, style prompting via natural language… pic.twitter.com/pPF2UnZ399

— Replicate (@replicate) 15 avril 2026

Gemini 3.1 Flash TTS You can steer how the model speaks by dropping tags right into the text: "[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?" 70+ languages, style prompting via natural language

→ View original post on X — @replicate