AI pet podcast
Turn your pet into a podcast host.
Upload one photo. Give them something to say. You get back a short video of your pet saying it.
Every sample says the same line: “Okay, we need to talk about the food situation.”
Free clips are 8 seconds. Files are deleted 24 hours after they are made.
Getting a good result
What works best
- A close-up where the face fills most of the frame. Distant shots often come back with the mouth barely moving.
- The sharpest photo you have — the video is only as clear as the photo you give it.
- Facing the camera, or turned slightly. Extreme angles are unreliable.
- Dogs and cats are what we've tested. Other animals may work; we make no promise.
About the shape of the video
The output keeps close to the shape of the photo you upload, but snaps to a standard frame. If you want a vertical clip for Reels or Shorts, crop your photo to 9:16 before uploading — that's the reliable way to get one.
How long it takes
A few minutes, sometimes longer. The wait depends on the queue rather than on how long your clip is, so we don't show a countdown we'd have to break. The timer shows how long you've actually been waiting.
What it doesn't do
- It doesn't write the line for you. That part is yours.
- Cloned voices are one-off. There's no saved voice library yet — that needs accounts.
- It doesn't make long videos. Free clips are 8 seconds.
- It won't reliably handle two pets in one photo, or a pet mid-motion.
Your files
Your photo, the audio and the finished video are kept in private storage and deleted automatically 24 hours after they are made. We don't use them to train anything. You must own the rights to whatever you upload — see our acceptable use policy.
Also here
Already have a video?
If you want to change what someone says in footage you already have, that's a different tool. Try the lip sync tool.