Copy link to clipboard
Copied
I failed to transcribe two audio files separately. Two different persons speak in each file.
As it was the first time for me to try the auto-transcript, I first selected "Mix" for the target audio in transcription settings. It worked. A transcript for two speakers was generated.
Then, I tried to transcribe one of the audio files. It keeps returning the transcript of two people talking as a result.
I wanted to do this separately because I wanted to put captions in different positions (by speakers).
Audio file information:
- length: 2 hours
- language: Japanese
Thank you!
Copy link to clipboard
Copied
Even if you get multiple transcripts, you'll have a problem of not being able to get two caption tracks made from them to show in your sequence. Also, I suspect that PR only allows one transcript per sequence.
The current workaround (assuming you are trying to burn in both speakers with different positioning/caption styling etc), is to create a caption track for each speaker in DIFFERENT sequences, then nest the sequences. See this post regarding this method:
Also to clarify, each of the two files contains one speaker. You use this to create a different audio track for each speaker. If you put these assets into different Sequences, can you create a transcript for each speaker?
Stan
Copy link to clipboard
Copied
That's exactly what I was wondering! Thanks!