 The study uses bioacoustics and metabarcoding to measure tropical forest recovery in Ecuador and shows that the community composition of vocalizing vertebrates reflects the restoration gradient. Two automated measures, an acoustic index model and a bird community composition derived from a convolutional neural network, correlated well with restoration and reflected the composition of non-vocalizing nocturnal insects identified via metabarcoding. The study demonstrates that new technologies can effectively monitor the success of forest recovery using robust and reproducible data. This article was authored by George Muller, Oliver Mitusser, H. Martin Schaefer and others.