With Gemini 2.0 Flash, Google introduced Multimodal Live API. This allows multiple tools to be called at once and Gemini to create TTS directly. Could this be added to HA’s Google AI integration?
With Gemini 2.0 Flash, Google introduced Multimodal Live API. This allows multiple tools to be called at once and Gemini to create TTS directly. Could this be added to HA’s Google AI integration?