Based on Solaria (with some heavy post processing).
Generating AI audio appears to be significantly ahead of AI video. One can use reasonably good AI singer voices, on the other hand, trying to generate a video clip feels like leaving it to chance, and getting lucky some times. Little to no control to generate a cohesive story.
Also, Synthesizer V - great tool! I wish more good voices, especially men were available.
Welcome to the forum. Nice song. I like the structure with the sound effects. My only voice suggestion would be to remember she needs to breath. You have some very long vocal lines. Even a quick BR to trigger a breath will help with realism. Try singing the lines yourself out loud and that will tell you where the breath pauses need to be.
remember she needs to breath […]
Try singing the lines yourself out loud and that will tell you where the breath pauses need to be.
That’s an insightful suggestion I hadn’t considered. It’s fascinating to learn, especially transitioning from the digital realm, with its fewer “constraints”, back to the tangible world. I find the process exciting, regarding both instruments and the human voice as I run daily into new things I never thought about! Alright, time to get back to work and address this.