Skip to main content
After your file uploads and you click Continue, Velo takes you to the Select Voice page. This is where you preview your video and pick the AI presenter - called a VeloTwin - whose voice will narrate your Velo.

​
Previewing your recording

At the top of the page you’ll see a video player with your uploaded recording. Play it back to confirm the right file was uploaded and everything looks correct before committing to generation. Below the player, the usage bar shows:
  • How many Velo Minutes this recording will consume
  • How many Velo Minutes you have remaining on your plan

​
Selecting a VeloTwin

The Select Your VeloTwin section shows your available AI presenters. Each card displays a thumbnail and the presenter’s name with their accent (for example, “Drew - American” or “Viraj - Indian”). Click the play icon on any card to hear a voice preview before selecting. Choose the one that best fits your brand and audience.
Your VeloTwin cannot be changed after Velo generation. Choose carefully - this selection is locked once you click “Go, Make my Velo.”

​
Public VeloTwins vs. My VeloTwins

The Public VeloTwins tab shows Velo’s built-in library of AI presenters. The My VeloTwins tab shows any custom VeloTwins you’ve created using your own voice and likeness. Learn how to create one in the Creating VeloTwin section.
Selecting a VeloTwin here sets the narration voice only. If you want to add the presenter’s face as a camera overlay in your video, you can do that in the editor after generation. See Add VeloTwin Face.

​
Generating your Velo

Once you’ve selected a VeloTwin, click Go, Make my Velo →. Velo will process your recording through several stages - you’ll see status messages like Preparing your file… and Detecting zoom regions… with a progress percentage. This typically takes under a minute for short recordings. When processing is complete, you’ll land on the preview page where you can watch your generated Velo and head into the editor.