Google enhances Gemini AI with new Canvas and Audio Overview tools

New Delhi: Google has unveiled two features for its Gemini AI platform—Canvas and Audio Overview.

The first feature, Canvas, introduces an interactive workspace within Gemini where users can create, edit, and refine both documents and code in real-time. Available on both web and mobile platforms, Canvas allows users to draft content—such as essays, speeches, or blog posts—and receive instant AI-powered suggestions to tweak tone, length, or formatting. 

For example, a user can highlight a paragraph and ask Gemini to make it more concise or professional, with changes reflected immediately. Beyond text, Canvas doubles as a coding companion, enabling developers to generate and preview prototypes like web apps, Python scripts, or HTML designs. A live preview feature lets coders see their work evolve as they make adjustments, streamlining the creative process.

For those looking to collaborate further, Canvas integrates with Google Docs, allowing users to export their work with a single click.

Originally debuted in Google’s NotebookLM, Audio Overview tool feature converts uploaded documents, slides, or even Deep Research reports into podcast-style discussions. Two AI-generated hosts narrate the content, summarising key points, drawing connections, and offering unique perspectives in a lively back-and-forth. Users can upload files via the Gemini prompt bar, trigger the “Generate Audio Overview” option, and download or share the resulting audio for later listening. While currently limited to English, Google has promised to expand language support in the future.

Both features are rolling out globally to all Gemini users, including those on the free tier, as of this week. However, the coding preview in Canvas remains web-only for now.