ResearchTasksVisual Text-to-SpeechVisual Text-to-SpeechFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGRIDStyleDubber10.9WER10Mar 11, 2026ChemGT3.5WER10Mar 11, 2026GRID (seen-speaker)ProDubber12.1WER5Jun 4, 2026LRS2 zero-shotGT8.93WER5Jun 4, 2026