Google has begun rolling out a new feature in Docs that allows users to create audio versions of their documents thanks to AI from Gemini. This capability is the latest in a series of AI innovations that the technology giant has quietly enabled over the past month within its Google Workspace ecosystem.
The Gemini audio feature in Google Docs enables users to listen to the content of their documents easily, with the option to select from seven different narrators:
“Whether you wish to listen to your content read aloud, better assimilate information while reading, or catch writing errors, audio versions of your documents offer clear and natural voices that read your documents aloud. You may also personalize your audio experience with various voices and playback speeds according to your preferences,” explains Google.
To play a document’s content, you will need to go to the “Tools” menu, select the “Audio” option, and click on “Listen to this tab”.
Additionally, authors of a document now have the option to create “audio buttons” that enable anyone accessing the document to play its content easily with a single click. To add one, simply open the “Insert” menu and select “Audio buttons”. Afterwards, if desired, it is possible to configure its label, color, and size.
At present, this feature is available only in English on the desktop web version of Google Docs for Google Workspace users subscribed to the Business Standard and Plus plans, Enterprise Standard and Plus, customers with the Gemini Education or Gemini Education Premium add-ons, customers with the Gemini Business or Gemini Enterprise add-ons, and subscribers to Google AI Pro and Ultra.
Google has not yet announced when it will enable the Docs audio feature in other languages and versions.
When accessing the “Insert” option located in the top menu of any Google Docs document, users will find new and interesting features.
One of these is the “Simple Decision Log”, included under the “Creation Elements” section. By selecting this new tool, a table is automatically created with the fields “topic,” “decision,” “owner,” and “status.” This offers an easy way to organize key decisions and keep an up-to-date view of each one’s progress.
Within the same “Creation Elements” section, there is also a “Task Tracking Table” option, which allows for orderly tracking of tasks to be completed and their current status.
In addition, the “Page Elements” section has been updated. It now includes the following options: table of contents, header, footer, watermark, page numbers, and footnote.
Google has introduced two new AI-driven image editing features in its Slides and Vids products: background removal and background expansion.
To access these options, you must first select the image you wish to edit, then click the “Generate an image” button located at the top of the sidebar on the right and select the “Edit” option. At this point, depending on your intent, you may select “Expand” to set a new aspect ratio, or “Replace background” to input a prompt with instructions for the new image.
Currently, this feature is available only in Google Workspace in English within the United States.
Google already allowed its Workspace users to generate images using Gemini AI in the web version of Google Docs, but it has recently extended this capability to the mobile version on Android. You simply need to select the Gemini icon (the four-pointed star) and describe the work you wish to create. Once generated, the image can be saved, copied, or inserted into a document.
This capability is now active in Workspace across multiple regions and languages, including Spain.
Google has upgraded the capabilities of Gemini in Google Drive, enabling it to leverage a context window of 1 million tokens to answer Workspace users’ questions about PDFs they are viewing. In this way, users may obtain detailed and summarized information effortlessly.
Photo: Depositphotos
Your email address will not be published. Required fields are marked *
Δ