I chose to do a video that is more of an overview of the world because the GPT used to create characters but after I switched the settings to make images in the 16:9 ratio it stopped producing the characters it used to.
I used ElevenLabs for the voice over audio in the voice of “Nicole” as I thought her deeper raspy voice was more fitting. I used Stable Audio to create the music. I used DALL-E for images and Runway for the movement in the images.
A challenge that I faced was not being able to increase the volume of sounds as I didn’t know how. The voice over is really quiet because it’s over the music. I generated some audio sounds using Audiogen App that I couldn’t use. I made sounds for the water and the city, but I didn’t know how to edit the sounds in since the voice over the music sounded wonky, I didn’t want to add more to it. Another challenge was not being able to use all of the script I generated for the video. I had a script describing each scene, but the voice over was too slow for talking. The entire script was about a minute thirty, but my video is only fifty seconds long.