- Oct 24, 2022
- 1,135
- 1,378
I see it can be done using 3 ways
first, you can extract the audio and transcript it then push that transcript into the video as subtitles but I think 50% of the results won't be accurate
the second way you can use an API for an existing AI model
or you train your model but I don't see it necessary to train your model
if I was in your situation I will use the second way
first, you can extract the audio and transcript it then push that transcript into the video as subtitles but I think 50% of the results won't be accurate
the second way you can use an API for an existing AI model
or you train your model but I don't see it necessary to train your model
if I was in your situation I will use the second way