Google Gemini now lets users generate, preview, and edit files directly inside chat on web and mobile, including PDFs, with full-screen document viewing and in-chat prompts to edit, such as turning a highlighted table into a graph.

The workflow is consolidated, allowing generation and editing to happen within Gemini without switching to separate apps.

Users are advised to confirm function scope and plan details relevant to their use case before implementation.

The announcement does not specify platform-specific coverage for each format, editing depth, file size limits, or detailed workflows.

Support is broad and language-agnostic where Gemini is offered, though compatibility varies by file type across platforms.

Language-based limitations are removed, enabling cross-language teams to work with mixed file types within Gemini.

The capabilities are now available to all users in every language where the Gemini app is available, with no staged delays announced.

Gemini’s document capabilities have expanded to all languages supported by the app, enabling broader multilingual use.

The rollout is global and universal across supported languages, without announced phased delays.

Broader language access and multi-format support can reduce the need to switch between separate document tools for common tasks.

This update follows prior Gemini releases and is part of Google’s ongoing Gemini product expansion.

Businesses should verify pricing, plan requirements, regional availability, and the full set of editing capabilities before adopting.