Ability to have subtitles in the video if we upload the audio for the avatar instead of text to speech

Currently, the subtitles of the video will not appear if we use our own audio for the avatar to lip sync. Appreciate if the team can consider generating the subtitles based on our audio uploaded. For info, I upload mainly cos there is no voice cloning yet in Jogg.

In case, this will be additional cost to JoggAI for the transcription. It is not an issue for me to enter the script for each scene manually.