Google has started rolling out an audio summary in Google Docs using Gemmi, a powered element for users to quickly get a summary of their documents via audio.
The update extends the current capability of Text to Speech, which was introduced in August 2025. Text to Speech takes text and converts it into an audio file that can be accessed via Gemini. This update takes the capability a step further to condense the text into a summary instead of reading out the whole text.
The feature developed by Google generates an audio summary which presents a document overview that includes information from all open browser tabs. Users can access a summary for their key points instead of reading through complete reports and detailed notes. The majority of summaries last less than three minutes, and they use voices that sound natural.
Users can personalise their listening experience through the selection of various voice styles, which include narrator, persuader and coach. The system allows users to modify playback speed from 0.5x to 2x.
On the web version of Docs, the option appears under the Tools menu. Alongside the existing “Listen to this tab” feature, users will now see “Listen to document summary”. Selecting it opens an audio player with playback controls, a timeline scrubber and voice style options.
The tool is designed to help users quickly review meeting notes before discussions, catch up on long reports while multitasking or follow along with their writing to improve clarity and spot potential errors.
The feature has no separate admin or end-user controls. It is rolling out to Rapid Release and Scheduled Release domains, with full visibility potentially taking more than 15 days.
Audio summaries are available for: