: Uses speech-to-text to display a transcript of the audio, allowing you to edit sound by searching for specific words.

: Automatically identifies different speakers in a single file to apply distinct processing to each.

: Optimized for Apple M-series chips for faster processing and lower CPU usage.

: Greater visual clarity in the spectrogram for manual "surgical" editing.

: Rebuilt from the ground up to automatically detect and fix noise, clipping, and clicks.