This study aims to develop an automatic speech recognition (ASR) system for the Bodo language using the Kaldi toolkit. Bodo, a Tibeto-Burman language spoken in the northeastern region of India, is considered a low-resource language due to the limited availability of linguistic data. The Kaldi toolkit, known for its flexibility and extensive support for various acoustic models and finite-state transducers, is employed to build a robust ASR system. The project involves the creation of a pronunciation dictionary followed by acoustic and language models. Various feature extraction techniques and model training algorithms are explored to enhance the system’s accuracy. The performance of the developed ASR system is evaluated using standard metrics, and the results demonstrate significant improvements in recognizing Bodo speech. This work aims to contribute to the preservation and technological advancement of the Bodo language, providing a foundation for further research and development in speech technologies for low-resource languages.