SuperMaker AI has introduced its new service to create realistic movies, images, speech, and music by leveraging the power of generative artificial intelligence.
Users only need to type the text to be spoken to receive AI-generated speech. For music, a description of the desired music is sufficient in Simple mode. In Custom mode, users can enter lyrics to be sung, then select the genre, mood, voice, and tempo to generate songs. For images and movies, an example image or movie can be used as a reference, or a new one can be generated based on a description of what is desired.
After the requests are submitted, SuperMaker AI requires a few dozen seconds or more to create realistic media. All new users receive 20 free starter credits, allowing them to create up to two videos (10 credits each), four songs (5 credits each), ten images (2 credits each), and four voice tracks (5 credits each). A login is not required to try the service, but free users cannot download the output.
A subscription provides additional credits and is required to download the generated media. The basic $9.90 per month plan provides 200 credits per month, the $29.90 mid-tier plan provides 800 credits, and the $49.90 top-tier plan provides 1,800 credits. A yearly subscription lowers the overall cost.
Readers who want to tinker with AI locally on their PCs can use a fast Nvidia graphics card (like this one on Amazon) with open-source software like Wan2GP on GitHub.