Security and duty
We’ve proactively assessed potential dangers all through each stage of the event course of for these native audio options, utilizing what we’ve realized to tell our mitigation methods. We validate these measures by way of rigorous inside and exterior security evaluations, together with complete purple teaming for accountable deployment. Moreover, all audio outputs from our fashions are embedded with SynthID, our watermarking expertise, to make sure transparency by making AI-generated audio identifiable.
Native audio capabilities for builders
We’re bringing native audio outputs to Gemini 2.5 fashions, giving builders new capabilities to construct richer, extra interactive functions by way of the Gemini API in Google AI Studio or Vertex AI.
To start exploring, builders can attempt native audio dialog with Gemini 2.5 Flash preview in Google AI Studio’s stream tab. Controllable speech era (TTS) is obtainable in preview for each Gemini 2.5 Professional and Flash by deciding on speech era within the generate media tab inside Google AI Studio.
