If you mean just the dialog, you'd do better starting from the 5.1 audio as a source. The centre channel should be dialog only.
If you want to include the music, or if you only have the audio as stereo, then it's not possible.
You cannot unbake a cake.
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.
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.
Below is copied from https://superuser.com/a/1271834/347380 & consequently I have changed this post to Community Wiki so I don't benefit from any points it may accrue in future.
Audacity – 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. using
ffmpeg -i video.mp4 -c:a pcm_s16le audio.wav
And then load the
audio.wav file into Audacity:
If you only want to get background music, select the Remove Vocals option; if you want the opposite, choose Isolate Vocals.
Note that this is never going to sound perfect. Vocal isolation is a hard task, as everything you hear is basically mixed into two tracks. An algorithm will never be as good as your brain in isolating different sound sources. Your audio source should be a stereo file with the vocals being panned dead-center. It might also produce false-positives, removing other instruments in the process.