This chapter explores the multifaceted domain of explainable artificial intelligence (XAI), emphasizing its critical role in fostering transparency, trust, and accountability in AI systems. It begins by clarifying the concept of explainability and its foundational role in human-AI interaction. The chapter then surveys a range of explanation techniques, including both intrinsic and post-hoc methods, and discusses strategies for enhancing model interpretability. It examines varying levels of transparency and the specific challenges of explainability in deep learning models. The discussion extends to bias detection and mitigation, highlighting their importance in ensuring fairness and reliability. Societal and ethical dimensions are addressed through the lens of human-centred XAI and responsible AI practices. The chapter also considers the role of explainability in auditing AI systems, particularly in high-risk applications, and concludes with an overview of emerging global regulatory frameworks aimed at governing the deployment of transparent and accountable AI.