Stanza is an open-source Python natural language processing (NLP) toolkit that supports 66 human languages. It features a fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. Stanza has been trained on 112 datasets, including Universal Dependencies treebanks and other multilingual corpora, demonstrating its ability to generalize well across different languages. Additionally, Stanza includes a Python interface to the Java Stanford CoreNLP software, extending its functionality to tasks such as coreference resolution and relation extraction. The toolkit is designed to be flexible and efficient, with support for different hardware devices and customizable pipelines. Performance evaluations show that Stanza achieves competitive or state-of-the-art performance on various datasets, making it a powerful tool for multilingual NLP research and applications.Stanza is an open-source Python natural language processing (NLP) toolkit that supports 66 human languages. It features a fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. Stanza has been trained on 112 datasets, including Universal Dependencies treebanks and other multilingual corpora, demonstrating its ability to generalize well across different languages. Additionally, Stanza includes a Python interface to the Java Stanford CoreNLP software, extending its functionality to tasks such as coreference resolution and relation extraction. The toolkit is designed to be flexible and efficient, with support for different hardware devices and customizable pipelines. Performance evaluations show that Stanza achieves competitive or state-of-the-art performance on various datasets, making it a powerful tool for multilingual NLP research and applications.