The video at a glance
- Video length
- 6 or 11 secondsChoose the short reaction or the longer scene.
- Frame & quality
- 9:16 or 16:9 · 720p MP4Vertical for a phone, landscape for a wider scene.
- Generation cost
- 10 / 20 credits6 / 11 seconds respectively. One driver photo per new video.
- Audio
- Template dialogue addedThe original template audio is added after generation. Exact lip sync is not guaranteed.
- Watermark
- No added site watermarkWe do not overlay a logo. AI can still produce unwanted text or marks.
- Photo deletion
- No automatic deletion deadlineDelete uploads and finished videos in Settings → Files. Contact support to remove intermediate images. Providers have separate retention rules.
Does the video retain the original audio?
The picture is generated first, then the matching recorded template audio is added. The 11-second version uses the selected full template track; the 6-second version uses an excerpt. It is not new dialogue generated from your photo, and it does not clone your voice.
Adding the recording does not guarantee lip sync. Listen to the whole download and check the mouth movement. “Original audio” describes the template recording, not a license for every way you might publish it.
Which frame should I choose?
Use 9:16 when you want a tall phone-feed video; choose 16:9 for a wider composition. Both request 720p output. Framing can change during generation, so keep the subject’s face away from the edges when you prepare the input photo.
Is the download watermark-free?
The service does not overlay a logo or site watermark. That does not guarantee the AI will never render stray text or markings in the scene. Review the final MP4 before posting.
Does an 11-second video take 11 seconds to generate?
No. Eleven seconds is the output duration. Processing also includes queueing, input checks, rendering, output checks and audio composition, with no fixed turnaround guarantee. Follow the saved task’s status in My videos.
What does the template not do?
The template replaces the pickup driver. It is not a free-form scene editor, and it does not guarantee exact likeness, natural pet anatomy or perfectly matched speech. The visitor may remain off-camera. Check the completed clip rather than judging only its poster frame.