I’d like to suggest adding proper lip-sync support for singing — meaning a character should be able to move their mouth according to a song, not just spoken audio. This feature is very important for creators making music videos.

At the same time, I’m facing a serious problem: when I try to upload my own song in mp3 or wav format, the system freezes. It stays at 0%, never loads the audio, and after a while, I get only a black screen with the chat logo. No video is generated, no preview — nothing happens.

The music I’m uploading is my own original song created with Suno AI, so there are no copyright issues.

I’ve tested this with different songs, using both videos and still images. The issue is consistent and clearly related to how Vozo handles audio input. Please fix this — and also consider expanding lip-sync to fully support singing. Thank you.