Google is preparing voice cloning capabilities for AI Studio, signaled by a hidden “Create Your Voice” option that appears when selecting the Flash native audio preview model, currently tied to Gemini 2.5 Flash. Selecting this option reveals a pop-up for recording and uploading audio, though the feature remains inactive. The presence of this capability indicates that Google is likely working toward a rollout of a more advanced native audio model, possibly Gemini 3 Flash, with voice cloning enabled. If this is released, it would let developers generate synthetic voices based on user-provided samples, adding a new layer of personalization for AI-generated audio responses.
This development targets AI Studio users who require customizable audio content, such as app developers building assistants or accessibility tools. While voice cloning is available elsewhere, direct integration with Gemini models would simplify the workflow for those invested in Google’s ecosystem. The actual release timeline is unannounced, but preparatory steps are visible in the UI.
Additional upcoming features were also found. In the build section, a new attachment option, Import from GitHub, suggests users will be able to bring entire repositories into AI Studio, turning codebases into workable projects within the platform. This could streamline onboarding for developers moving projects into Google’s environment, although integration details, especially around supported frameworks, are still unclear. Broader backend capabilities, such as database and Firebase integration, remain in the pipeline.
The homepage is also being updated, splitting activity summaries and usage statistics, with previously teased comment panels included. These changes reflect Google’s continued effort to position AI Studio as a comprehensive, developer-focused platform as the underlying Gemini models advance. The pace of updates suggests that some of these features may become available in the near future, depending on internal testing and stability.
As Google continues expanding AI Studio’s scope, voice cloning, GitHub integration, and improved navigation could attract both new and existing developers looking to experiment with Gemini-powered workflows. The direction aligns with Google’s recent push to provide flexible, full-stack tooling for AI application builders.
