Abstract
Artificial Intelligence (AI) is increasingly shaping the modern world through applications in healthcare, finance, education, and communication. While its global adoption grows, AI's potential for solving localized problems, particularly in linguistically diverse and underserved regions remains underexplored. One such application is in the enhancement of indigenous languages through Natural Language Processing (NLP), which enables native speakers to access digital services in their mother tongues. This paper introduces the Lédèe Yorùbá API, an AI-driven system developed to promote linguistic and financial inclusion for Yorùbá-speaking communities in Nigeria. The API integrates speech recognition, context-aware translation, and a financial glossary engine to facilitate native-language interaction with fintech platforms, USSD systems, and mobile applications. Training data was obtained from real-world interactions with urban and rural users, as well as language corpora from leading Nigerian universities. Evaluation results show high performance in glossary accuracy (97%), speech-to-text (88%), and user satisfaction, particularly among students and traders. Compared to global platforms like Google Translate, the API demonstrates superior tonal accuracy and dialect sensitivity. The system not only enhances digital participation among non-English speakers but also fosters cultural preservation. Future work involves scaling to other indigenous languages, strengthening financial integrations, and contributing open datasets. The Lédèe Yorùbá API offers a replicable model for inclusive, language-centered AI innovation.

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2025 Tech-Sphere Journal for Pure and Applied Sciences