1. I see that you plan to introduce voice cloning. How many voices? Which tier available to? ETA?
2. For each scene, how long? I.e. how long can the end result be? Will this get longer as tech improves?
3. Multiple voices in same video? Dialogues/conversations?
4. Possible to create ai video podcast (vodcast)?
5. Can a story character from one video be reused for another e.g. to create a coherent video series of various episodes
6. What aspect ratios?