Feature Ideas

Lighter version of rendering/lipsync allowing to create avatars instantly from photo

In addition to facial dynamic expressions, we can add avatar gesture control.

Add templates consisting of several pages. 16x9 templates.

Arms moving exactly the same way at the beginning of each new scene still lets the avatar look automated. Maybe you can add a figure like random movements? Or randomizing the movement itself?

Is it possible to change avatar clothes based on text prompts like in other ai video generators?

Make voice slower/faster to adjust text and avatar

Add the ability to place two avatars on the same stage, each with their own separate script.

Add subtitles to videos you create.

Choose an avatar then Click the FaceSwap icon. Upload clear, camera-facing photos of a person's face. Avoid side face photos, overexposure, and blocked faces. Click on a photo to swap faces.

The possibility to listen to the music before adding it to the video.

We are all the time working on increasing the speed of video generation and already shortened generation time, but not stopping there!

Option to download the generated audio from the script

Now: every video generated entirely Suggestion: In case you need to generate 100x similar videos with one slide changed, only changing part will be generated (and you will be charged only for this part)