Here's How to Upload Audio to Google Gemini AI

Google has expanded the capabilities of its Gemini AI app, enabling users to upload and analyze audio files directly within the chatbot. Previously limited to text and select document formats, Gemini now accepts music clips, podcasts, interviews, and other voice recordings for analysis and queries.

The update also introduces ZIP file support, allowing multiple documents to be uploaded simultaneously.

Josh Woodward, Vice President of Google Labs, confirmed on X (formerly Twitter) that audio uploads were the most requested feature by Gemini users. Gemini already processes text, images, videos, and PDFs, but the addition of audio enables broader applications for both professional and educational use.

Students can upload lecture recordings, musicians can test song snippets, and business professionals can analyze interviews or meeting audio.

Upload Limits for Free and Paid Users

The feature comes with plan-specific restrictions:

* Free Users: Audio files up to 10 minutes with 5 prompts per day.

* Google AI Pro and AI Ultra Users: Audio uploads up to 3 hours and 10 files per day across all supported formats.

ZIP uploads can contain a maximum of 10 files. For code or GitHub repository uploads, users can add up to 5,000 files per session, capped at 100MB.

Gemini now supports multiple file types:

* Documents and Text: txt, doc, docx, PDF, RTF, Google Docs, hwp, hwpx

* Spreadsheets: xls, xlsx, csv, tsv, Google Sheets

* Media: images, videos, audio

* Archives: ZIP

How to Upload Audio in Gemini

1. Update or download the Gemini app from Google Play Store or App Store.

2. Log in with a Google account.

3. Tap the Upload icon within a chat window.

4. Select an audio file, such as a podcast or recording.

5. Type a question, e.g., “Summarize this audio” or “What are the key points?”

6. Gemini processes the audio and delivers results instantly, within plan limitations.