Official BytePlus partnerBytePlus, a ByteDance company
Official BytePlus partner · Talking pets
Make your pet talk: one photo, any voice
To make a pet talk, upload one clear photo of your dog or cat to KreatorFlow Lip Sync, add a voice line (typed or recorded), and press Generate. OmniHuman 2.0 moves the mouth to every word and adds natural head movement, in a video up to 5 minutes long.
- Dogs, cats and other pets
- Your voice or ours
- Talks or sings
- 720p or 1080p
- 4 credits per second
Last updated
On this page
What a talking pet video is
A talking pet video is made from a still photo: the animal looks at the camera and speaks a line in the voice you chose, with the jaw, muzzle and head moving in time with the words. KreatorFlow does this with Lip Sync, which runs ByteDance's OmniHuman 2.0 model through BytePlus (KreatorFlow is an official partner of BytePlus, a ByteDance company).
You do not need your pet to sit still for a camera, and you do not need editing skills. The photo you already have on your phone is usually enough.
How to make a pet talk in three steps
- 1
Pick a photo of your pet
Choose a sharp photo where your dog, cat or other pet faces the camera and its mouth and muzzle are easy to see. A head-and-shoulders shot works better than a whole pet far away in the garden.
- 2
Give your pet a voice
Type the line and pick one of our voices, or upload an MP3 or WAV: your own recording, a friend doing the voice, or a line made in the Audio studio. The audio can be 4 seconds to 5 minutes long.
- 3
Generate the talking pet video
Choose 720p or 1080p and press Generate. The price shows first (4 credits per second at 720p). The video is as long as the audio and saves to your library.
Tips for a convincing talking pet
- Face the camera. A pet looking at you, or close to it, gives the model a clear mouth to work with. Profiles and faces turned away give weaker results.
- Get close. Head and shoulders, filling most of the frame. Crop a wide photo before you upload it.
- Keep the mouth clear. No toy, ball or bowl in front of the muzzle, and not a photo mid-yawn with the tongue out.
- Use good light. Dark fur in a dim room loses detail around the mouth. Daylight by a window works well.
- Start short. A one or two sentence line at 720p tells you quickly whether the photo works before you make a longer clip.
- Direct the moment, not the look. Use the optional direction for movement only, for example “The dog tilts its head, then leans towards the camera on the last word.” Do not describe the dog; the photo already does that.
More lip sync examples
Real results: one picture and one voice track or song in, a talking video out.
Singing
“City lights are calling me home, I don't want to walk these streets alone.”
16 seconds at 720p · English · An original soul song made in the Audio studio
Two people, one speaker
“Okay, so here's the thing nobody tells you about starting a podcast. The first ten episodes? Nobody listens…”
14 seconds at 720p · English · The Jonah voice
A painting that speaks French
“Trois cents ans immobile dans ce musée, à sourire aux touristes. Enfin, quelqu'un me laisse parler. Merci, mes amis.”
7 seconds at 720p · French · A French Text to Speech voice
An anime character in Japanese
“こんばんは！雪がきれいですね。今日はずっと、あなたに会いたかったんです。”
6 seconds at 720p · Japanese · A Japanese Text to Speech voice
Real results from KreatorFlow Lip Sync, each made from one AI-generated picture (no real people) and audio from our Audio studio. Press play to hear them. AI-generated video.
Ideas for a talking pet
Birthday message from the dog
The family dog wishes someone happy birthday in a voice you recorded.
Your pet's side of the story
A short confession or complaint for social posts, like the sandwich example above.
Pet shop or groomer promo
A happy customer's pet (with the owner's permission) announces this week's offer.
Adoption appeal
A rescue animal introduces itself in its own voice, in a shelter's post.
A pet that sings
Your cat performs a song you have the rights to, for a funny reel.
Brand mascot
A company dog or cat becomes the voice of your channel, in the same voice every time.
Choosing the voice
Recording the voice yourself is the most personal option: speak the line on your phone in the voice you imagine for your pet and upload the file. If you would rather type, pick one of the English voices on the Lip Sync page; the line is made with Text to Speech first. For other languages or more voices, make the line with Text to Speech in the Audio studio and pick it in Lip Sync.
Consent and responsible use
Lip Sync makes the person in a photo say whatever the audio says, so it comes with clear rules. On the website you confirm, the first time you generate with a new photo, that you are that person or have their permission. Photos are screened before anything is charged, and photos with nudity or of minors are refused.
- Use a photo of yourself, or of someone who has given you permission to make them speak. A character you created, an animal or a drawing is fine.
- Use a voice you have the right to use: your own, one of our voices, a voice you cloned with consent, or a recording you have permission for. The same goes for any music or song.
- No sexual content, nothing involving anyone under 18, and no impersonation: never make a real person appear to say something they did not say in order to mislead, harass or defraud.
- No celebrities, politicians or other public figures unless they have given you permission and you hold the rights for that use.
- When you post a talking video of a real person, say that it is AI-generated. Many platforms require that label.
Read the full rules in the Acceptable Use Policy on real people's faces and the Terms.
Talking pet questions
How do I make my dog or cat talk in a video?
Open Lip Sync on KreatorFlow, upload a clear photo of your pet, then type what it should say and pick a voice, or upload a recording. Press Generate. OmniHuman 2.0 moves the mouth to the words and adds head and face movement, so the pet looks like it is really speaking.
Which animals work?
Dogs and cats give the most reliable results because their face and mouth are easy to read. Other animals with a clear face, such as a rabbit, a horse or a parrot, can work too. The clearer the face and mouth in the photo, the better the result.
Do I need a video of my pet?
No. Lip Sync starts from one still photo. It does not re-voice a video you already filmed; if you only have a video, take a sharp still frame from it and use that as the photo.
What voice should my pet have?
Anything you have the right to use. Many people record the voice themselves on their phone, which costs nothing extra and sounds personal. You can also type the line and use one of our voices (2 credits per 1,000 characters for the voice line), or clone your own voice in the Audio studio.
How much does a talking pet video cost?
4 credits per second of audio at 720p and 6 at 1080p, with a 4-second minimum. A 10-second clip costs 40 credits at 720p. You see the price before you generate, and credits for a failed video come back.
Can I make a pet talk for free?
No. Lip Sync is for paid accounts: any plan, from $15 for the first month on Creator, or a credit pack from $8.
Can my pet sing?
Yes. Upload a vocal track you have the rights to and the pet sings it. A clean vocal with quiet music gives the most convincing mouth movement.
Can a person be in the photo with the pet?
It is better to use a photo with only the pet, so the voice goes to the right face. If a person is in the frame, they must be you or someone who agreed, and you can say in the direction which one speaks.
Give your pet a voice
Add a photo of your pet and a voice line, and see the price before you generate. Available on any paid plan or credit pack.