Google Rolls Out Real-Time Captions for Gemini Live, Enhancing Accessibility and User Experience

Google Introduces Real-Time Captions for Gemini Live

Google has rolled out a significant update to its Gemini Live AI chatbot, introducing real-time captions that promise to enhance user experience and accessibility. This new feature allows users to interact with Gemini without relying on audio output, making it more versatile in various environments 1

1

How It Works

The real-time caption feature is activated via a new square icon located in the top-right corner of the Gemini Live interface. When enabled, captions appear near the bottom of the screen, displaying Gemini's responses as they are generated. This functionality extends to screen sharing and live video features within Gemini Live 2

2

Source: Gadgets 360

Improved Accessibility and Usability

One of the most significant improvements is that Gemini Live no longer requires users to have their device volume turned up. Previously, the app wouldn't open unless the volume was at an audible level. Now, if the device's volume is turned down, Gemini Live automatically suggests enabling captions, making it much more user-friendly in quiet or noise-sensitive environments 1

1

Customization Options

For Android users, Google has included customization options for the captions. A new "Caption preferences" setting allows users to modify:

• Language
• Text size
• Caption style (including font style, text color, background color, and opacity)

These options provide users with the ability to tailor the caption appearance to their preferences and needs 2

2

Related Stories

Google Launches Free Voice-Powered AI Chat for Android Users

Google Enhances Gemini Live with Visual Guidance and Native Audio Model

Google Gemini Live gets biggest update ever with human-like conversational AI upgrades

Google's Gemini Live: Free Voice AI Assistant Now Available for Android Users

Availability and Rollout

Source: Android Police

The real-time caption feature is being rolled out globally to both Android and iOS users. It's available in the stable (v16.23) and beta versions of the Google app on Android. While the feature functions similarly on both operating systems, the customization options are currently only available on Android devices 1

1

2

Limitations and Future Improvements

It's worth noting that the real-time captions only display Gemini's responses, not the user's input. Additionally, the captions show only the current response, not the entire conversation history. To view the full transcript, users must end the session. These limitations suggest potential areas for future improvements to the feature 2

2

This update represents a significant step forward in making AI chatbots more accessible and user-friendly. By eliminating the need for audio output, Google has made Gemini Live more versatile and suitable for use in a wider range of situations, from quiet offices to noisy public spaces.