Some questions

[gelsas]

I have quite a unique use case I think.

I have videos with a length of lets say 3 seconds that have english voiceover. Now I have generated a spanish voice over using text to speech. The spanish voice over is 5 seconds long. Just speeding up the spanish audio will not work since it would sound way to fast. Just slowing down the video also does not work it would look way to slow.

Can I use any of the features of your tool to find the optimal adjustments that would need to be made to the find the best adjustment values between video and spanish voice. What I mean is that I get something like, slow down video by factor X and speed up audio by factor X. so that the adjustments are the least noticable.

I am not sure if your tool supports something like this.

---

And two additional questions: could you explain this with an example to me I am not entirely sure I understand what this one does exactly: Speech-to-translated-transcript alignment. and for this one as well: Speech-to-transcript alignment