Google Docs gets 'Audio': Know about Gemini-powered text-to-speech feature

Gemini in Google Docs now allows users to generate audio versions of documents, offering realistic voices, custom playback speeds, and multitasking convenience

Google announced in a blog that it has started rolling out a new AI-powered feature in Google Docs. With this update in place, Gemini will turn written documents into spoken audio. According to Google, this will make it easier to listen while multitasking, follow along for better comprehension, or spot mistakes in your writing. The tool offers realistic, natural-sounding voices and lets users adjust playback speed or switch between different voice styles to suit their preferences. Google said that the rollout will be completed by the end of this month.

 

Notably, at the moment, this audio feature is only available in English and on desktop. 

 

Google Gemini audio feature in Google Docs: Availability

This new feature is available for Google AI Pro and Ultra subscribers, as well as Business, Enterprise, and Education plans.

How to use Google Docs text-to-speech feature

As per the company, this feature is designed for both writers and readers, giving each the option to listen to documents instead of only reading them.

 

Readers can access the Listen to this tab option, available in the Tools > Audio menu, to quickly listen to the contents of the current tab.

 

Authors can add Audio buttons, available in the Insert > Audio buttons menu, which inserts a play button directly into documents so readers can easily listen to the current tab with a single click. Once added to the document, authors can change the label, color, and size of the button. 

   

Google NotebookLM also has a similar feature, named Audio Overviews, which turns written text into realistic-sounding podcasts. However, that feature works a bit differently; it doesn’t just turn the text into an audio version, but rather converts it into a conversation or a discussion between two people.