gemini-3-1-flash-tts-824d4742·1 events·first seen Aliases: Gemini 3.1 Flash TTS
DeepMind has released Gemini 3.1 Flash TTS, a new audio model focused on expressive speech generation. The model introduces granular audio tags that allow developers precise control over AI speech output. This represents an incremental advancement in Google's text-to-speech capabilities within the Gemini model family.