Skip to content
RRanked By Task

This Week

Gemini API takes older Office files and tool media

Google's 5 November 2026 Gemini API notes add PPT, ODP, ODS, and DOC page images, and let tool results return Office files, audio, and video.

Official source (opens in a new tab)

Google's Gemini API release notes for 5 November 2026 expand Office and OpenDocument input. The API now accepts PowerPoint 97-2003 (PPT), OpenDocument Presentation (ODP), and OpenDocument Spreadsheet (ODS). It also adds page-image processing for Word 97-2003 (DOC). Google says DOC, PPT, and ODP files are rendered as page images. For ODS, the model receives the data and formulas from the first sheet. Processing for DOCX, DOTX, ODT, PPTX, XLSX, and XLS is unchanged.

The same note says tools can return Office and OpenDocument files, audio, and video to the model. On the GenerateContent API, function response parts now accept those types in addition to images, PDFs, and plain text, and they accept fileData so a tool can return a Files API URI instead of inline bytes. displayName is available on both inlineData and fileData. Video parts accept mediaProcessing set to STATIC or AGENTIC. On the Interactions API, function_result steps accept document, audio, and video blocks, by inline data or uri, in addition to text and image. Video blocks are in v1beta and v1alpha and accept processing.

Who it's for: a developer whose Gemini tool or upload has to hand the model an older Office file, a spreadsheet formula, or an audio or video result.

Fits: Best for Writing stays Claude. Gemini stays third. This is an API file format, not a change to the chat ranking. The Gemini start guide and the Gemini alternatives are unchanged. The verdict is unchanged.