GoogleOn August 27, a blog post was published, announcing that Gemini AI supports more types of files and provides users with better AI services by analyzing, extracting, and gaining insights into document content.
Google says that Google Workspace users with Gemini Business, Enterprise, Education, or Education Premium licenses can now upload a variety of files to Gemini (gemini.google.com) from Google Drive or local devices:
- spreadsheet:Gemini AI can now process spreadsheets in formats such as CSV, XLSX, and ODS, enabling users to analyze numerical data, track trends, and generate insights from financial models, sales reports, and more.
- Presentation:Users can now upload presentations in formats such as PPTX, PDF, and KEY, allowing Gemini AI to extract key points, summarize content, and identify visual elements such as charts and images.
- image:Gemini AI can now analyze images in formats such as JPEG, PNG, and GIF to extract text, identify objects, and provide context for visual content.
- Audio:Users can now upload audio files in formats such as MP3, WAV, and FLAC, allowing Gemini AI to transcribe speech, identify speakers, and summarize key points from interviews, podcasts, and lectures.
- video:Gemini AI can now process video files in MP4, MOV, and AVI formats to extract scripts, identify scenes, and summarize key events from presentations, documentaries, and training videos.
According to the press release, Gemini can analyze user-uploaded files more specifically based on prompt words entered by users, summarize complex topics, identify trends and insights, and provide suggestions for improved writing and document organization, helping users improve their understanding, research, and writing skills.