Safety and responsibility
We’ve proactively assessed potential risks throughout every stage of the event process for these native audio features, using what we’ve learned to tell our mitigation strategies. We validate these measures through rigorous internal and external safety evaluations, including comprehensive red teaming for responsible deployment. Moreover, all audio outputs from our models are embedded with SynthID, our watermarking technology, to make sure transparency by making AI-generated audio identifiable.
Native audio capabilities for developers
We’re bringing native audio outputs to Gemini 2.5 models, giving developers latest capabilities to construct richer, more interactive applications via the Gemini API in Google AI Studio or Vertex AI.
To start exploring, developers can try native audio dialog with Gemini 2.5 Flash preview in Google AI Studio’s stream tab. Controllable speech generation (TTS) is on the market in preview for each Gemini 2.5 Pro and Flash by choosing speech generation within the generate media tab inside Google AI Studio.
