In the latest developments surrounding the Gemini Android app, a notable feature has emerged that hints at the potential for audio file integration. Users may soon find themselves able to attach audio files, such as MP3s, directly to their chats with Gemini.
New Features on the Horizon
Recent findings from an APK teardown of version 16.30.59.sa.arm64 of the Google app beta reveal a promising new capability. This feature allows users to attach audio files during conversations with Gemini, accompanied by a suggestion to “Talk live about this.” While this sounds intriguing, it is important to note that the functionality is not yet fully operational.
Upon uploading an audio file, users have the option to either type a question or select the “talk live” prompt. However, the current response from Gemini is inconsistent; it may overlook the audio entirely or generate inaccurate responses. Such occurrences are not uncommon in chatbot interactions, where misinterpretations can lead to unexpected results.
Despite these initial hiccups, the underlying technology suggests a promising future. The developer side of Gemini already demonstrates an ability to process audio input via its API. This includes capabilities such as summarizing, transcribing, and even responding to specific timestamp requests within audio files. Supported formats include MP3, WAV, and FLAC, indicating a robust framework for audio analysis.
While the audio attachment feature is still in its infancy, it aligns with the recent introduction of image uploads in the Gemini app, signaling a logical progression toward enhanced multimedia support. As the development continues, users remain hopeful for a seamless integration that will allow for richer interactions with the Gemini platform.
