🪄World Labs’ 3D AI Magic

Fei-Fei Li’s World Labs unveils interactive 3D AI scene generator

Key Points 

• World Labs’ AI transforms a single image into an interactive 3D scene that users can explore and modify.

• Unlike other models, World Labs’ 3D scenes remain consistent and follow basic physics for a more realistic feel.

👨🏻‍💻News - World Labs, a startup founded by AI pioneer Fei-Fei Li, has introduced its first project: an AI system capable of generating 3D video game-like scenes from a single image. 

✨What makes it unique? While many AI systems can turn photos into 3D models, World Labs sets itself apart by offering interactive, modifiable scenes. Users can explore the scenes using a keyboard and mouse, adjusting settings like the depth of field for added realism. The results, although slightly cartoonish, are rendered live in the browser and offer a level of control that most AI systems don’t provide.

👾How does it compare? This technology falls under the "world models" category, which simulates 3D environments. Unlike competitors like Decart’s Oasis, which struggles with resolution and consistency, World Labs’ scenes maintain their structure and obey basic laws of physics, providing a solid, realistic feel.

🤹🏻‍♂️What’s more? World Labs also adds interactive features, such as changing object colors and dynamic lighting effects. Though it’s still in an early preview phase with limited exploration capabilities and occasional rendering errors, the startup plans to develop tools for professionals in fields like gaming, design, and filmmaking. 

Hume AI launches tool for custom AI voices

Key Points 

• Hume AI’s Voice Control lets users create custom AI voices with real-time adjustments, no coding required.

• The tool uses a slider interface to fine-tune attributes like gender, confidence, and enthusiasm for personalized voice design.

📢News – Hume AI, a startup focused on emotionally intelligent voice interfaces, has launched Voice Control, an experimental feature that allows developers and users to create custom AI voices without the need for coding, AI prompt engineering, or sound design skills.

🎙️How so? The tool allows for real-time adjustments to various voice attributes, such as gender, assertiveness, enthusiasm, and confidence, through a simple slider interface. It’s available in Hume’s virtual playground, accessible with a free user sign-up.

🗣️Why this matters – This release tackles a common challenge in the AI industry, where preset voices often fall short for specific brands or applications. By focusing on customization, Hume aligns with its broader goal of enhancing emotionally nuanced voice AI while reducing risks tied to voice cloning.

👀See also – Hume plans to enhance Voice Control with more adjustable dimensions, improve voice quality under extreme adjustments, and expand the range of base voices available.