Google Gemini to Introduce Customizable Voice Model Settings

Google is expanding the capabilities of its AI assistant, Gemini, by introducing new features for personalized voice interactions. Currently, users can select from preset voice models like Orbit, Pegasus, and Ursa, but deeper customization options are on the way.

Analysis of the latest beta version of the Google Android app (17.41.12.sa.arm64) reveals that developers are implementing four adjustable parameters: speed, energy, warmth, and formality. These settings will be presented as sliders, allowing users to adapt voice output to their preferences. For example, speed will control speech pace, while energy will influence intonational expressiveness, independent of pace.

While the feature is still in testing and does not yet affect real voice output, it is expected that users will eventually save their chosen settings for consistent use. The update may also introduce a new voice model selection interface with smooth transition animations between options.

These changes align with the growing trend of multimodal interfaces in AI systems, making interactions more natural and adaptable. Google has not disclosed an exact release date, but the update could arrive within the next few months.