What is the Gemini App?
Gemini is Google’s smart AI app. You can ask it questions, give it files, and it will read, understand, and answer based on them.
Earlier, you could only upload PDFs and text files (like documents) to Gemini. But now, Google has added something exciting!
New Feature: Upload Audio Files
On Monday, Google announced that Gemini can now accept audio files too.
This means you can upload things like:
- Music samples
- Interviews
- Voice recordings
The AI will listen to them, understand what’s inside, and answer your queries.
More File Types Supported
Not just audio—Gemini also supports ZIP files now.
A ZIP file is like a folder that holds many files together in one package.
Here’s what Gemini can now take:
- Text files (txt, doc, docx, PDF, RTF, Google Docs, etc.)
- Data files (xls, xlsx, csv, tsv, Google Sheets)
- Images and videos
- Audio files (new!)
- ZIP files (but only up to 10 documents inside)
Works on Both Android and iOS
Josh Woodward, Vice President at Google Labs, shared the news on X (Twitter).
He said this feature is coming to both:
- Android Gemini app
- iOS Gemini app
So no matter which phone you use, you can enjoy the feature!
Limits for Free and Paid Users
Just like images and videos, audio uploads also come with limits:
-
Free Users:
- Can upload 10 minutes of audio
- Get 5 free prompts (questions) per day
-
Pro & Ultra Users:
- Can upload up to 3 hours of audio
- Can upload 10 files per day across all formats
For coding projects (like GitHub repositories), Gemini even allows 5,000 files (up to 100MB in size) in one chat session! That’s huge.
Why This is Special
This new feature is a big step forward because:
- You can now ask AI about songs, speeches, or voice notes.
- You can share folders using ZIP documents.
- It supports almost every common document format.
- Developers can use it for big coding tasks too.
It makes Gemini smarter, more flexible, and valuable for everyone—from students to professionals.
Point of view
With this update, Google Gemini does not just understand text—it can now listen to audio too!
Imagine uploading a recording of your institute lecture, a podcast, or even your favorite song, and Gemini helping you understand it better.
This makes learning and creating with AI even more fun and powerful.