This systematic review explores the use of audio analysis and artificial intelligence (AI) in diagnosing respiratory diseases. It examines 75 studies across three main areas: (a) cough detection, (b) identification of lower respiratory symptoms, and (c) diagnostics from voice and speech. The review highlights the increasing use of machine learning (ML) algorithms to analyze audio-based biomarkers such as cough sounds, respiratory sounds, and voice/speech sounds. These biomarkers are valuable indicators of respiratory functionality and can be used to detect diseases like asthma, COPD, COVID-19, and others. The review also discusses the use of publicly available datasets and the impact of the pandemic on research trends, with a surge in studies on COVID-19 diagnosis, mobile data acquisition, and remote diagnosis systems. Key findings include high accuracy in cough classification, the use of ML models such as SVM, K-NN, and CNN, and the importance of feature extraction and preprocessing techniques. The review also addresses the challenges in automated respiratory disease identification and the potential of AI to improve diagnostic accuracy and reduce the need for invasive procedures. The study concludes that AI and ML have the potential to revolutionize respiratory disease diagnosis by enabling quick, accurate, and remote diagnosis.This systematic review explores the use of audio analysis and artificial intelligence (AI) in diagnosing respiratory diseases. It examines 75 studies across three main areas: (a) cough detection, (b) identification of lower respiratory symptoms, and (c) diagnostics from voice and speech. The review highlights the increasing use of machine learning (ML) algorithms to analyze audio-based biomarkers such as cough sounds, respiratory sounds, and voice/speech sounds. These biomarkers are valuable indicators of respiratory functionality and can be used to detect diseases like asthma, COPD, COVID-19, and others. The review also discusses the use of publicly available datasets and the impact of the pandemic on research trends, with a surge in studies on COVID-19 diagnosis, mobile data acquisition, and remote diagnosis systems. Key findings include high accuracy in cough classification, the use of ML models such as SVM, K-NN, and CNN, and the importance of feature extraction and preprocessing techniques. The review also addresses the challenges in automated respiratory disease identification and the potential of AI to improve diagnostic accuracy and reduce the need for invasive procedures. The study concludes that AI and ML have the potential to revolutionize respiratory disease diagnosis by enabling quick, accurate, and remote diagnosis.