Google Gemini Now Supports Audio File Uploads for Transcription and Analysis

Google has added a highly requested audio upload feature to its Gemini AI. Users can now submit audio files directly through the Gemini app on Android, iOS, and the web. This new capability allows for transcription, summarization, and content extraction.

The feature was confirmed by Google VP Josh Woodward. He noted that audio support was the single biggest user request since Gemini’s launch.

How To Use The New Audio Feature

Users can upload files by tapping the file button in the Gemini app. The system accepts a wide range of common audio formats. This includes MP3, WAV, and M4A files.

There are specific limits to this new function. You can upload up to 10 files at one time. The total combined length of these files cannot exceed 10 minutes. Standard Gemini usage rates and limits still apply to these queries.

According to Reuters, this update is part of a broader push to make Gemini a more versatile assistant. It provides a practical tool for students, professionals, and journalists. They can now quickly get transcripts from lectures, meetings, or interviews.

Broader Impact and Future Developments

This move signals Google’s commitment to evolving its AI platform. It directly addresses a key gap between Gemini and other AI services. The ability to process multimodal inputs is crucial for modern AI assistants.

The feature is currently in a gradual rollout phase. Not all users have access to it immediately. Google typically enables new features server-side over several days.

This audio functionality is a step toward a promised major Gemini redesign. Future updates will introduce a new card-based interface for interacting with on-screen content. The goal is to fully replace the older Google Assistant with Gemini.

Google’s Gemini audio upload feature marks a significant expansion of its AI capabilities. This update directly responds to strong user demand for more versatile file support. The tool positions Gemini as a more complete productivity assistant for modern needs.

Info at your fingertips

What audio file formats does Gemini support?

Gemini supports common formats like MP3, WAV, and M4A. The system can process most standard audio files. Uncompressed formats may have larger file size limitations.

Is there a limit to how many files I can upload?

Yes, you can upload a maximum of 10 files at once. The total audio length cannot exceed 10 minutes. These limits help manage server load and processing times.

Can Gemini translate uploaded audio files?

Gemini can primarily transcribe and summarize audio content. Translation capabilities may depend on the languages involved. The system is optimized for English processing first.

When will all users get access to this feature?

Google is rolling out the feature gradually over several days. Some users may have access immediately. Others might need to wait for the update to reach their accounts.

Does this work on the free version of Gemini?

Yes, the audio upload feature is available on the standard free tier. It is subject to Gemini’s standard usage limits. Gemini Advanced subscribers may receive higher quality outputs.

Trusted Sources

Google Official Support Documentation, Reuters