AI Model Preset: Select from Tiny, Base, Small, Medium, or Large Turbo. 'Base (Balanced)' is the default mode, while ‘Large Turbo’ provides the highest accuracy.
Transcription Language: Select the language spoken in the video to improve transcription precision.
Audio Preprocessing: The 'Use prefilter for better accuracy' option is checked by default. It reduces background noise and optimizes audio levels before transcription.
Clear Model Cache: Delete the downloaded AI models from the app's data folder.