Text to Speech + Voice Cloning, so we can upload a script that will be read by AI. For the video part, we can already use the video clips from the library, but an audiogram feature wouldn't gram.

As a non-English speaker, voice cloning for educational videos is essential for me. Reading lengthy text while maintaining eye contact with the camera and keeping the audience engaged can be challenging. Voice cloning would be a game-changer, especially if it allows me to upload transcripts and convert them into speech for B-roll footage.