Video Localization by adding subtitles and dubbing

I have a video that I need localized into both Lithuanian and Estonian, by adding subtitles and dubbing.

I already have translates text in both languages.
I want you to use Elevenlabs voice (Mark - ConvoAI) / Eleven v3 (alpha) model or any other tool with similar sounding.

Main point - has to sound natural in Lithuanian and Estonian.

Video is 3min. long

My problem is that each time I generated voice in Elevenlabs it was about 20% longer/slower than what is on actual video.

So I had to either delete a lot of pauses in Elevenlabs audio that takes too much time or speed it up, but then it doesnt sound natural anymore to match what is actually happening in the video.

If you make satisfactory work in total I have 20 videos, each 3-6min long that I need to be localised in Lithuanian and Estonian languages.

Afterwards also may need on ongoing basis for shorts videos.