Gemini 2.5 Flash TTS is Google's text-to-speech model built on the Gemini 2.5 Flash architecture, designed for real-time voice assistants, high-volume narration, and conversational applications. It supports 24 languages with fine-grained control over voice style and pacing, and can maintain consistent character voices across multi-speaker scenarios. The model features enhanced expressivity that aligns with style prompts and adjusts pacing based on context, making it well-suited for interactive voice agents and dynamic audio content production.
API|상용 모델
