Feature requests, feedback and ideas for the HeyGen team

Product feedback & requests

I’ve been testing the Video Agent and wanted to share a few early observations.

I pushed a project to 59 scenes using Unlimited mode. The full training video runs a little over 12 minutes. The voice quality has been surprisingly strong, and in this case the agent recommended not using an avatar because the slides and media were the primary focus. That guidance made sense once I saw the output.

One adjustment for me is the workflow itself. I am not sure I have saved time yet because the agent prefers breaking scenes after a certain amount of time or text, which creates more scene management than I expected.

The biggest mindset shift is editing through intent instead of timeline control. You cannot directly edit the video plan. You have to tell the agent what outcome you want rather than how to execute it. For example, saying “Use image XYZ on scene 35” instead of “Insert slide at 232 seconds and display for 5 seconds, then show slide ABC.”

That part will take some getting used to.

One thing that did stand out was script generation. The cadence and natural delivery from the Video Agent felt noticeably better than what I typically get starting from scratch.

I will keep sharing what I learn as I continue experimenting.

Video Agent Feedback (Ugentic User)

Home

Forum

Events

Content

People

Contributors

Albums

Groups

Chat

Channels

Tools

Help

Connect with the community, find inspiration, and learn how to make your best videos. 

HeyGen

Dive deeper in the Geniverse. Learn, connect and level up with HeyGen.

HeyGen Community

Login to the HeyGen community to connect with others, attend community events, and more!

Login or Sign Up for even more

To unlock all parts of the community and get the best experience, complete your profile.