Google’s Gemini 3.1 Flash TTS model offers unparalleled control over AI voices

1 · Siliconangle · April 16, 2026, 12:19 a.m.
Summary
Google's DeepMind has launched the Gemini 3.1 Flash TTS model, which significantly improves text-to-speech technology by allowing users to control vocal style, delivery, and pace through text commands. This marks a shift from previous, more robotic TTS models to a more customizable and user-friendly experience.