According to Android Authority, the latest beta version of the Gemini Android application, specifically version 16.30.59.sa.arm64 of the Google app beta, indicates upcoming support for audio file attachments in chats. Users can now observe an option to attach audio files, such as MP3s, to their conversations within the app.
Upon attaching an audio file, a new prompt, “Talk live about this,” appears. However, despite this promising suggestion, the audio processing functionality is not yet fully operational. When an audio file is uploaded, Gemini currently struggles to comprehend or respond to the content in a meaningful way. In some instances, the application completely ignores the attached audio file, while in others, it may provide confident but fabricated information, a phenomenon known as chatbot hallucination, which is not exclusive to audio files or Gemini.
Despite the current limitations, the integration of audio file support aligns with Gemini’s existing capabilities on the developer side. The Gemini API already supports audio input, allowing developers to feed audio and request descriptions, summaries, or transcriptions of the content. The API can also handle timestamp-specific requests, such as “from 2:30 to 3:29,” and is compatible with various audio formats, including MP3, WAV, and FLAC.
This suggests that Google is likely developing a similar robust audio processing feature for the Android application. While the current implementation appears to be a placeholder rather than a finished product, the move towards audio support is considered a logical progression, especially given that image uploads are already widely available within the Gemini app. There is no official timeline for the full launch of this feature.
