Seply uses AI to separate voices from a single recording. You upload audio or video, and it creates a time-aligned WAV track for each speaker it detects, which you can preview and download.
It handles common formats such as WAV, MP3, M4A, FLAC, MP4 and MOV, and supports more than 30 languages. There is nothing to install and no manual cutting required. It is free to try after signing in.
