# Google DeepMind — Multimodal file processing and slicing

- Company: Google DeepMind (deepmind.google)
- Announced: 2026-11-18
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://ai.google.dev/gemini-api/docs/changelog#11-18-2026
- Record: https://forck.live/items/37857-multimodal-file-processing-and-slicing
- Subject: Gemini API

Google's Gemini API now accepts Microsoft Office and OpenDocument files, including Word, PowerPoint and Excel, directly in requests. Developers can also slice documents, spreadsheets, videos and audio inside user prompts and function responses, selecting page ranges, worksheet tabs, cell ranges, time intervals or content layers such as page images, extracted text, formulas or video transcripts. Google says the slicing lets callers process and pay only for the content they need. The changelog points to its document, video and audio understanding pages for setup details.

## Evidence

Verbatim from https://ai.google.dev/gemini-api/docs/changelog#11-18-2026:

> You can now pass Microsoft Office and OpenDocument files (Word, PowerPoint, and Excel) directly to the Gemini API, and slice documents, spreadsheets, videos, and audio in user prompts and function responses. Select specific page ranges, worksheet tabs, cell ranges, time intervals, or content layers (such as page images, extracted text, formulas, or video transcripts) so you only process and pay for the content you need.
> 
> To get started, see Document understanding, Video understanding, and Audio understanding.

---

Record: https://forck.live/items/37857-multimodal-file-processing-and-slicing
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
