VOICE AND PROMPTING

The backend agent listens for voice commands and prompting, and continuously captures the current mesh state and the user’s conversation.
It interprets gestures and spoken prompts in real time, matching the evolving 3D geometry with the intended aesthetic.
The model is fine-tuned for generating excellent FLUX (ImageGen) prompts, that then can be translated into 3D Gen Models.
They are highly precise and structured outputs, with controlled variables (such as setting and lighting) and are automatically formatted as strings in the specified JSON schema.

{
"subject": {
"name": "stackable chair",
"form_keywords": ["curved shell", "mono-block", "faceted"],
"material_keywords": ["brushed aluminum", "matte ABS", "polished steel"],
"color_keywords": ["graphite gray", "satin sand", "electric blue"]
}
}

This ensures the system translates intent into actionable design parameters for shape, material, and color, maintaining clarity and consistency throughout the generative workflow.