Let's Talk, Not Type: An Oral-First Multi-Agent Architecture for Guaran\'i

ArXi:2603.05743v1 Announce Type: new Although artificial intelligence (AI) and Human-Computer Interaction (HCI) systems are often presented as universal solutions, their design remains predominantly text-first, underserving primarily oral languages and indigenous communities. This position paper uses Guaran\'i, an official and widely spoken language of Paraguay, as a to argue that language in AI remains insufficient unless it aligns with lived oral practices. We propose an alternative to the standard "text-to-speech" pipeline, proposing instead an oral-first multi-agent architecture.