How do I make a UGC video with a talking presenter in ChatGPT?

Generate a 9:16 selfie-style frame of a fictional presenter holding your product, then animate it with Gemini Omni Flash and quote the exact lines to speak. Gemini Omni Flash adds lip-synced speech and natural sound in one generation of up to 10 seconds.

By Itay Dressler, Creative Claw · Updated

Steps

  1. Attach a clear product photo and write about 20–25 words in a creator’s voice: a hook, one real benefit, and a close.
  2. Ask Creative Claw to generate a 9:16 selfie frame of a fictional presenter holding the product with the label facing the camera, using your photo as the reference.
  3. Approve the frame, then ask for a 10-second Gemini Omni Flash video that starts from it. Quote the lines and say how to pronounce the brand name.
  4. Transcribe the result, trim any repeated or wrong words with a jump cut, and add captions with the brand spelled correctly.

What it costs

The presenter frame costs 16 credits and a 10-second 1080p Gemini Omni Flash clip costs 260 credits. Our finished example, including the product reference and transcript, cost 294 credits ($2.94).

Still stuck? Email [email protected] with the job ID, or browse all help articles.