
Performance and technical.Īs several have mentioned, the first thing is to not sound like you're doing dictation. I'll be somewhat comprehensive so you can work it out based on your resources and needs. Some are simple and cheap strictly within Audacity. I don't know how much of this type of recording you're going to be doing. I've also listened to your sample, so I can speak from a reference point. It might also produce false-positives, removing other instruments in the process.I know I'm rather late to the question, but I'll go ahead and throw in my two cents.


Your audio source should be a stereo file with the vocals being panned dead-center. An algorithm will never be as good as your brain in isolating different sound sources. Vocal isolation is a hard task, as everything you hear is basically mixed into two tracks. Note that this is never going to sound perfect. If you only want to get background music, select the Remove Vocals option if you want the opposite, choose Isolate Vocals. using ffmpeg: ffmpeg -i video.mp4 -c:a pcm_s16le audio.wavĪnd then load the audio.wav file into Audacity: I've tried it, it kind of works if you get lucky - which is less than you'd really hope for but about as much as you can expect.īelow is copied from & consequently I have changed this post to Community Wiki so I don't benefit from any points it may accrue in future.Īudacity – a free and open-source cross-platform audio editor – can do this, using the Vocal Reduction and Isolation effect.You should first extract the audio from the video file, e.g.

There is now the very good yet very expensive Izotope RX which has a "Music Rebalance" plugin which can attempt the same type of thing. If you want to include the music, or if you only have the audio as stereo, then it's not possible. The centre channel should be dialog only. If you mean just the dialog, you'd do better starting from the 5.1 audio as a source.
