Google is developing a new customization feature for its Gemini AI assistant that allows users to adjust vocal characteristics, including speed, energy, formality, and warmth. Recent code analysis of the Google app version 17.41.12 beta, reported by 9to5Google, reveals that these settings will likely be accessible via a new menu, enabling more granular control over how the AI sounds during interactions.
Customizable Voice Parameters in Gemini
The discovery within the app’s APK files points to a shift toward personalized AI personas. Rather than selecting from a static list of pre-recorded voices, users may soon be able to manipulate the AI’s delivery using four distinct sliders. According to the findings, these parameters include:
- Speed: Options for slow, normal, and fast pacing.
- Energy: A multi-increment slider to adjust the enthusiasm or "vibrancy" of the voice.
- Formality: A setting to shift between casual and professional tone.
- Warmth: A control intended to adjust the emotional or friendly quality of the AI’s output.
These settings are designed to persist across both standard chat interactions and the Gemini Live conversational mode. By adjusting these variables, Google aims to provide a more tailored experience, allowing the assistant to sound more professional for research tasks or more conversational for casual planning.
Strategic Context and Market Competition
This development aligns with Google’s broader strategy to enhance the naturalness of its AI. At the Google I/O 2024 developer conference, the company previously signaled that it intends to introduce support for regional dialects to further localize the assistant’s tone and cultural relevance.
The push for vocal customization is part of a wider trend among major tech firms to differentiate their AI assistants. Apple has integrated similar concepts into its ecosystem; with its recent software updates, Apple allows users to adjust Siri’s pace and expressivity, though those settings are applied globally across Apple’s suite of services, including Maps and Safari.
Google’s approach, as indicated by the beta code, appears to prioritize deep personality configuration within the Gemini interface. While Google has not yet provided an official release date for these customization sliders, their appearance in the app’s beta code suggests that testing is underway.
Key Takeaways
- Granular Control: The proposed interface uses sliders to modify speed, energy, formality, and warmth rather than just selecting a voice profile.
- Persistence: Customized voice settings are expected to apply globally to both standard Gemini chats and Gemini Live sessions.
- Technical Basis: The feature was identified by 9to5Google through an analysis of version 17.41.12 of the Google app, which contained hidden code strings related to the new menu.
- Industry Trend: This update follows Apple’s introduction of similar voice-tuning tools for Siri, highlighting a competitive focus on the "humanization" of AI assistants.
Keep reading