You Can Finally Upload Audio Files To Gemini - Here's What You Need To Know
Google has steadily been updating Gemini since its debut in 2023, giving its AI chatbot more capabilities and functionality over time. Now, it looks like the company has finally addressed one of the biggest requests for the chatbot, at least according to Google's VP, by adding the option to upload and process audio files in the Gemini app on Android, iOS, and the web.
This is just the latest feature to make its way to Gemini, which has seen updates that add more personalization to Gemini, as well as Gemini's recent addition to Google Finance. The app is also set to get a makeover, which will see it utilize a new floating card-like system to interact with objects on your phone's display. That should make Gemini a true replacement for Google Assistant.
According to Google VP Josh Woodward, audio has been the "#1 request" from Gemini users, and now, users can use Gemini to transcribe audio files, summarize their contents, and more, directly from the File button in the Gemini app.
Using audio files in Gemini
Based on information shared in Google's official support document, users can upload up to 10 files at a time, though the total audio length can only be up to 10 minutes long. Additionally, other Gemini usage rates may apply to the use of these files in the app itself, so it's good to be mindful of those limitations before sending dozens of files Gemini's way.
It was already possible to talk to Gemini using Gemini Live, but this new functionality will allow users to upload raw audio files they've already captured directly to the app. For instance, if someone recorded a seminar or a work meeting, they can upload the audio file and use Gemini to transcribe it, create study notes, or just pull specific information from the file.
The feature appears to still be rolling out, though, and as of writing, I have not received the update in my Gemini app just yet. However, you may already have the feature available on your account. If you want to find out, upload an audio file and give Gemini a command. If it is able to process the audio file, then it will do so. If it can't, it will present you with a warning that it cannot process files of that type.