Cristian Pérez‐Granados, David Funosas, Jon Morant, Oscar Humberto Marín‐Gómez, Irene Mendoza, Miguel A. Mohedano-Muñoz, Eduardo Santamaría, Giulia Bastianelli, Alba Márquez‐Rodríguez, Michał Budka, Gérard Bota, José M. De la Peña‐Rubio, Eladio L. García de la Morena, Manu Santa‐Cruz, Pablo De la Nava, Mario Fernández‐Tizón, Hugo Sánchez‐Mateos, Adrián Barrero, Juán Traba, Tomasz S. Osiejuk, Patrick J. Hart, Amanda K. Navine, Agudelo Muñoz, Carlos Barros de Araújo, Gabriel L. M. Rosa, Ingrid M. D. Torres, Ana L. C. Catalano, Cássio Rachid Meireles de Almeida Simões, Diego Llusia, Manuel B. Morales, Pablo Acebes, Juan A. Medina Méndez, Nicholas Brown, Christos Astaras, Ilias Karmiris, Estanislao Aguayo Navarrete, Maxime Cauchoix, Luc Barbaro, Dominik Arend, Sandra Müeller, Fernando González‐García, Alberto González‐Romero, Christos Mammides, Michaelangelo Pontikis, Giordano Jacuzzi, Julian D. Olden, Sara Bombaci, Gabriel Marcacci, Alain Jacot, Juan Pablo Zurano, Elena Gangenova, Diego� Varela, Facundo G. Di Sallo, Gustavo A. Zurita, Andrey Atemasov, Junior A. Tremblay, Anja Hutschenreiter, Alan Monroy‐Ojeda, Mauricio Díaz‐Vallejo, Sergio Chaparro‐Herrera, Robert A. Briers, Renata S. Sousa‐Lima, Thiago Pinheiro, Walmir da Silva, Alice Calvente, Anamaria Dal Molin, Alexandre Antonelli, Svetlana S. Gogoleva, Igor Palko, Hiếu V. Trong, Marina H. L. Duarte, Natalia dos Santos Saturnino, Samuel R. Silva, Ana Rainho, Paula Lopes, Karl‐Ludwig Schuchmann, Marinêz Isaac Marques, Ana Silvia de Oliveira Tissiani, Nick A. Littlewood, Mao‐Ning Tuanmu, Yi-Ru Cheng, Hsuan Chao, Sebastian Kepfer‐Rojas, Andrea L. Aguilera, Lluís Brotons, Mariano J. Feldman, Louis Imbeau, Pooja Panwar, Aaron S. Weed, Anant Deshwal, Alfredo Attisano, Jörn Theuerkauf, Dorgival Diógenes Oliveira‐Júnior, Cicero Simão Lima‐Santos, Carlos Salustio‐Gomes, Raiane Vital da Paz, Mauro Pichorim, Eben Goodale, Esther Sebastián‐González
BirdNET is a popular machine learning tool for automated recognition of bird sounds. However, evidence on how to optimize its settings for accurate bird monitoring remains limited. Here, we evaluate how BirdNET settings influence model performance in identifying bird vocalizations and characterizing bird communities, using 4224 1‐min recordings from 67 recording locations worldwide. Giving equal importance to recall and precision, a low confidence score threshold (0.1–0.3) appears optimal for detecting bird vocalizations, whereas higher thresholds (around 0.5) are more suitable for characterizing bird communities. Based on our findings, we recommend increasing the Overlap parameter from its default value of 0 to 2 s, as this consistently improves BirdNET performance in detecting both bird vocalizations and species presence. The effect of the Sensitivity parameter varied across regions. However, a value of 0.5 maximizes global performance for community‐level analyses across all confidence thresholds, and a value of 1.5 generally yields better results for vocalization‐level studies, particularly at low confidence thresholds. Our findings offer practical guidance for selecting BirdNET settings in passive acoustic bird surveys, enhancing both the identification of bird vocalizations and the characterization of bird communities.