Three emotions
Joy, tears, then rage in one take: your photo acts a short script you can edit, voice and face following the feeling


- In
- One selfie
- Out
- A vertical talking video, lip-synced
- Engine
- HeyGen Avatar 4
- By hand
- One tap, the script in plain words, no timeline
Your photo speaks a script you write, in a chosen voice or a clone of yours. Vertical, lip-synced, up to 60 seconds, ready for TikTok, Reels or Shorts. The language follows the text.
Three emotions
Open the card with a selfie or one of your Doppelshot photos.
Write what it says. Pick a voice, or your own cloned voice.
Run it, then download the vertical video.
Talking video
Which voices are there?
About 30 voices in many languages, plus your own: record a short consent clip and Doppelshot clones your voice for every card.
How long is the video?
As long as the script, up to 60 seconds. Vertical 9:16, the format of TikTok, Reels and Shorts.
What does it cost?
The credits shown on the card, per 10 seconds of video. A failed video is redone for free or the credits come back.

