Medical documentation is an essential aspect of healthcare, and it is important to ensure that healthcare professionals have access to the necessary tools to improve their productivity. However, in African hospitals, with prevalent low doctor-to-patient ratios, the need for productivity-boosting tools is high, which are available in most developed countries (Simpson, 2005). One such tool is clinical speech-to-text technology, which can significantly reduce the time and effort required for clinical documentation. This is especially important considering the time-consuming and arduous nature of clinical documentation in African healthcare systems. To address this issue, a pan-African English ASR model is needed. This model would utilize a large and diverse accented English speech corpus of 200 hours, featuring 120 different African accents, to accurately transcribe clinical speech-to-text in a variety of African accents. The goal of this research was to provide healthcare professionals in health facilities with access to clinical speech recognition technology, thereby improving the efficiency, accuracy, and quality of clinical documentation in Africa. The objectives of this research project were to develop and evaluate a pan-African English ASR model for healthcare. The ASR model was developed to accurately transcribe clinical speech-to-text in a variety of African accents. The effectiveness and accuracy of the developed ASR model was evaluated and compared with other existing ASR models to ensure that it meets the needs and expectations of healthcare professionals in African clinics. This would enable doctors to spend more time attending to patients, leading to better healthcare outcomes and a higher quality of life for people in Africa. The research focused on a case study of selected hospitals in Nairobi County, Kenya, and the findings were valuable in improving the quality of healthcare across the continent.