Multimodal time series data are pervasive across various applications, providing detailed insights into the evolution of dynamic and complex systems with high-dimensional, high-resolution information. Analyzing the statistical characteristics, detecting changes, and uncovering unexpected behaviors over time from these longitudinal data can yield valuable insights. Traditional anomaly detection methods that rely solely on automated algorithms often overlook the context-specific nature of anomalies. To address this challenge, we introduce Anomalyzer, a novel visual interface for anomaly analysis with multimodal time series data at scale. Anomalyzer integrates sequential transformations to extract, refine, and analyze data representations crucial for anomaly analysis in complex multimodal time series data. Our approach offers a simple yet powerful workflow, a purposeful and step-by-step process meticulously crafted to guide users through the identification and analysis of anomalies with precision and clarity. We evaluate the performance of Anomalyzer with a synthetic multi-variate time series dataset, demonstrating the effectiveness of our novel approach in identifying and analyzing anomalies. The preliminary results have shown that Anomalyzer can help users to perform time series visualization and anomaly detection efficiently using its visualization, aggregation, and anomaly detection capabilities.