Google Docs Introduces Gemini-Powered Audio Playback for Documents
Google Docs now allows users to generate natural-sounding audio versions of their documents using Gemini. The feature offers customizable voices and playback speeds to improve accessibility and reading comprehension.
Google Docs introduces a new feature that allows users to listen to their documents using Gemini. This tool provides clear, natural-sounding audio that reads text aloud, which helps users absorb information, catch writing errors, or simply enjoy content hands-free. Listeners have the option to customize their experience by choosing from a variety of voices and adjusting playback speeds.
The functionality caters to both readers and authors by offering two distinct ways to access the audio. Readers can select the "Listen to this tab" option from the Tools > Audio menu to hear the current document content. Meanwhile, authors can insert interactive audio buttons directly into the text via the Insert > Audio buttons menu, allowing readers to play the audio with a single click and giving authors the ability to customize the button's label, color, and size.
This audio generation tool enhances document accessibility and engagement, though it currently comes with a few limitations. The feature is restricted to English and is only available on desktop platforms. It is rolling out to Rapid Release domains starting August 18, 2025, and Scheduled Release domains on August 25, 2025, with availability for various Google Workspace tiers and Gemini add-on subscribers.