Leverage the power of LLMS and Speech to Generate a Mp4 video of an Avatar spitting straight out custom RAPS
Plan ?
- Create a basic pipeline which will generate Rap lyrics given context, info about rap and duration
- Experiment on how this generated lyrics can be voiced-over [ T2S - Text 2 Speech Models ]
- Generate cool avatar which can be used to lipsync this audio
- Generate mp4 for the same