Opera introduces new AI image generation and voice output features in latest update

Opera continues to expand the capabilities of its browser with the introduction of new AI-driven features. The latest update to the Opera One Developer stream has introduced some very cool enhancements, including image generation and voice output capabilities, through its native AI, Aria.

Aria, Opera’s browser-based AI, now allows users to generate images directly from text prompts. This feature, powered by Google’s Imagen2 model, enables users to create unique visual content simply by describing their ideas in words. For instance, users can ask Aria to generate an image of a dog enjoying a vacation on a beach. If the initial result doesn’t meet expectations, there’s an option to regenerate the image with modifications, such as adding a drink or changing the color of the dog’s sunglasses.

This interactive process not only caters to those looking to enhance presentations or create engaging content but also adds a layer of customization by allowing users to refine their requests without restarting the conversation.

In addition to image generation, the update brings a voice output feature that enables Aria to read aloud text responses. This addition enhances accessibility and offers convenience for users who prefer auditory learning or need hands-free interaction. By clicking a speaker icon, users can hear Aria’s response in a lifelike voice, which can be paused or restarted as needed. This feature utilizes the Basic version of Google’s Wavenet model, ensuring the spoken output is clear and natural.

Users are encouraged to download the Developer version to experience these new features and provide feedback, helping to shape the future of Aria development.