Google adds audio uploads to Gemini

Cosmico - Google adds audio uploads to Gemini
Credit: Google Gemini/Alphabet, Inc.

Google rolled out three major updates to its Gemini-powered products on Monday, broadening the ways users can interact with its AI ecosystem. The Gemini app now accepts audio file uploads, Search gains support for five new languages, and NotebookLM introduces flexible new report formats.

Gemini App Gets Audio Support

Josh Woodward, vice president of Google Labs and Gemini, announced on X that audio compatibility had been the “#1 request” for the Gemini app. The update makes it possible to upload audio files directly into prompts, with some limits depending on subscription tier:

  • Free users: 10 minutes of audio per file, up to five prompts daily.
  • AI Pro and AI Ultra users: Uploads of up to three hours per file.

All users can attach up to 10 files in a single prompt, across multiple formats—including ZIP archives. The new feature makes Gemini more useful for tasks like transcriptions, summaries, or insights from voice notes and recorded meetings.

Search Adds Five New Languages

Gemini 2.5’s integration with Google Search has also unlocked new language options for AI Mode. Users can now interact in Hindi, Indonesian, Japanese, Korean, and Brazilian Portuguese, bringing deeper AI-assisted exploration to a wider global audience.

“With this expansion, more people can now use AI Mode to ask complex questions in their preferred language, while exploring the web more deeply,” Google noted in its blog.

NotebookLM Introduces New Report Formats

NotebookLM, Google’s Gemini-powered research tool, is also getting smarter. Already capable of analyzing text, audio, and other media, the software now generates reports in a variety of formats—including study guides, briefing documents, blog posts, flashcards, and quizzes—in more than 80 languages.

Users can tailor the output by adjusting tone, structure, and style, making NotebookLM more versatile for academic, professional, or personal use. Google says the feature should be fully rolled out by the end of the week.

A Rapid Pace of AI Updates

These updates continue Google’s breakneck rollout of AI features over the past two months. In August, Gemini introduced memory for recalling user preferences across conversations, while Workspace users gained access to the video generation tool Vids. September brought upgrades to Google Photos, including support for the new Veo 3 model and the ability for free users to create short silent videos from their own photos.

With audio input, multilingual search, and dynamic reporting, Google is signaling its intent to make Gemini a universal AI assistant—one that listens, speaks, and adapts across languages and formats.

Read more