Aria: Opera One’s AI gains image renderer and audio player

Integrated into the Opera One browser, Aria artificial intelligence (AI) has gained advanced features that allow: to produce synthesizes images and human voice text responses from textual descriptionsimproving interaction and accessibility. The features were announced this Monday (29) by Opera Software.

Using Google’s Imagen2 model, the browser’s artificial intelligence can now: create visual representations based on instructions provided by users via text prompt. This feature also makes it possible to recreate images according to each person’s needs, resulting in better results, according to the company.

Aria’s sound generation tool is based on the Wavenet model, also developed by Opera. Possible by adding Get answers to requests for productive AI in audio formatWe make technology more accessible.

“We believe these additions will significantly improve users’ browsing experience and offer new ways to interact with the browser. “We are committed to delivering innovative, cutting-edge features that meet users’ evolving needs,” commented Krystian Kolondra, Opera’s VP of Browsers and Games.

How does Arya work?

Just like ChatGPT, Gemini, and other chatbots, Opera One’s AI can be used to: searches related to recent events and execution of different tasks. One resource is Aria Compose, which helps you create text for emails, social media posts, and slides.

Totally free, he can do it too page summaries, generating codes, answering questions about Opera products, and more. The bot is available in both the computer browser and mobile app; the latter has Android and iOS versions.

Image renderer and audio duplicator coming first to Opera’s Developer edition One. After downloading, simply start a chat with Aria via the sidebar or command line to learn about new features.