Gemini Live on Android now offers users the ability to utilize captions, providing a quieter method of interacting with the assistant. This latest update is being rolled out through the Google app version 16.23, available on both stable and beta channels.
When initiating a Gemini Live session, a captions button will appear in the top-right corner. By tapping on it, a floating box will display a text version of Gemini's spoken responses. These captions will remain fixed in the middle of the screen, allowing for easy readability. While they do not show real-time transcription of the user's speech, the full transcript can still be accessed at the end of the session.
Captions are only visible when using the full-screen Live interface. Exiting this screen during a session will make the captions disappear, but they can be re-enabled by re-entering the screen before the session concludes. Once activated, the captions setting will persist for future conversations, eliminating the need to toggle it on each time.
A new 'Caption preferences' menu has been added to Gemini's settings, located under the 'Interrupt Live responses' toggle. This feature links to the system-level caption settings, granting users more control over the appearance of captions.
Previously, Gemini Live required the phone's volume to be at a certain level for conversations to begin. With this latest update, this limitation has been removed, allowing users to speak their prompts aloud and simply read the responses. This is particularly useful in quiet environments or when headphones are not available.
The introduction of captions to Gemini Live offers users a more flexible and convenient way to engage in voice conversations with AI. This update demonstrates Google's commitment to refining Gemini Live based on user feedback and real-world usage scenarios. If the feature is not immediately visible, restarting the Google app in the device settings may prompt the update to appear.
This incremental improvement enhances the usability of Gemini Live, making it more accessible and convenient for everyday use. While there is still room for growth, updates like these contribute to a more seamless and user-friendly experience.