I want to create voiceover in different language for .mp4 file which is in english. I have transcribed .mp4 using Whisperx and I have three files .txt and .srt/.vtt. I translated .txt/.srt/.vtt files into desired languages and took .txt file as an input to TTS - Elevens Lab service(I don't know if there is a service for creating tts for .srt too. I was looking for it but did not find any). Now I have TTS in .mp3 format with desired language but the problem is. TTS reads this .txt file as it is. Is there any option to somehow modify this .mp3 file so it would respect .srt/.vtt file timestamps? I am giving an example:
1 00:00:00,140 --> 00:00:05,050 This is an example of a subtitle file with a bunch of random words.
Translated: 1 00:00:00,140 --> 00:00:05,050 <Translated_text_in_diff_lang>
.txt content: This is an example of a subtitle file with a bunch of random words.
creating .mp3 file from .txt file Now I want this tts to speak in timestamps of .srt file
I tried to do it using software like Filimora, CapCut in terms of .srt to speech but it requires payment.
I can recommend Narakeet. You will have to pay beyond a certain number of minutes. I have tried Filmora and it chopped the files into one clip per time stamp for some reason. The biggest challenge is always if there is not enough time for the new voice to say what was said by original voice.