Google's Flash TTS gives developers director-level control over AI voices in 70+ languages
Google DeepMind launched Gemini 3.1 Flash TTS, a text-to-speech model that lets users direct vocal style, delivery, and pace through natural language commands. Scoring 1,211 on the Artificial Analysis TTS leaderboard, the model supports over 70 languages with regional accents and includes SynthID watermarks for detecting AI-generated content.