Audio Overview transforms documents, text and extensive notes or reports from Gemini’s Deep Research tool into an engaging, podcast-like audio discussion featuring two AI-voiced speakers.

I tried out controllable text reading with 'Gemini 2.5' in Google AI Studio - YouTube Native audio functionality is available in Google AI Studio, as well as in Vertex AI via the Gemini API.

Google has introduced a new AI tool in Gemini called Storybook, which lets you create 10-page storybooks, featuring ...

Overview Google AI Studio lets anyone use advanced Gemini models for text, image, and video tasks—no coding required.Users ...

Gemini 1.5 Pro could do for audio what previous versions did for text Gemini 1.5 Pro is touted as a major upgrade by Google, and audio processing could enable a host of new features.

To understand exactly what GPT-5 needs to deliver, I put ChatGPT-4o and o3 head-to-head with Gemini 2.5 Pro across three ...

Just like we already have on the web, new Canvas output options could soon be coming to the Gemini app on Android.

Current tools will transcribe the speech into text and then summarize the conversation based on the text. However, Gemini 1.5 will be able to cut out the middleman and listen to the audio directly.

Suggest edits: Gemini will recommend suggestions that you can accept. Canvas can be used as a basic text editor, while Google touts use cases like speeches, essays, blog posts, and reports.

"Simply describe any story you can imagine, and Gemini generates a unique 10-page book with custom art and audio," wrote the ...