ResearchTasksJoint text-to-audio-video generationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHDTF and Hallo3 English (test)Talker-T2AV24.32FID12Apr 28, 2026DH-FaceVid-1K Chinese (test)Talker-T2AV0.148CER6Apr 28, 2026