BunCho video tools
Make a talking avatar video from one image and a script
Pick one image of a person or character, then type the lines or upload an audio file. You get a video where that person speaks, with the mouth, face and head moving to the voice. Choose from five models and see the credit estimate before you generate.
Open the video tools Plans and pricing
Available on paid plans with an active subscription (not on the free plan or during the free trial). You see a credit estimate before anything is generated.
If you are not signed in, you sign in (or create an account) first and then land on the video tools.
What you put in, what you get
You provide
- One image of a person (one person, face clearly visible; PNG, JPEG or WebP; short side at least 300 px; aspect ratio between 1:2.5 and 2.5:1)
- Voice: a script (up to 300 characters, with a choice of four voices) or an audio file (up to 30 s)
- Extra direction (optional, e.g. "smiling, looking at the camera")
You get
An MP4 of the person in the image speaking the audio. The length matches the voice: 2–30 seconds.
Good for
- Have your own character, or one you made in the studio, read an announcement or greeting
- A narrator for explainers and shorts without showing your face
- Turn a story character's lines into a talking clip that keeps the manga art
Models you can choose and their credits
Kling Avatar 2.0 comes in Pro and Standard; Standard uses about half the credits of Pro. OmniHuman 1.5 also moves the hands and body but uses more credits. HeyGen Avatar IV outputs 1080p, and P-Video Avatar outputs 720p with the fewest credits. A common approach is to check the voice and image with a low-credit model, then make the final version with a higher-end one.
| Model | Length | Approx. credits | Difference |
|---|---|---|---|
| Kling Avatar 2.0 ProDefault | 2–30 s | about 438 for 5 s | High quality, takes a few minutes |
| Kling Avatar 2.0 Standard | 2–30 s | about 221 for 5 s | About half the credits of Pro, slightly lower quality |
| OmniHuman 1.5 | 2–30 s | about 667 for 5 s | Also moves hands and body, more credits |
| HeyGen Avatar IV | 2–30 s | about 194 for 5 s | Fewer credits, 1080p |
| P-Video Avatar | 2–30 s | about 126 for 5 s | Fewest credits, fast, 720p |
The estimate screen lists the credits for every model with the same input, so you can compare first and only generate when you agree.
How to make an AI avatar video
Choose the image
Open Video tools > AI avatar in the studio and upload one image. A front-facing image with a large, clear face works best.
Set the voice
Type the lines and pick a voice, or upload an audio file of up to 30 seconds.
Pick a model and get an estimate
Choose a model and press Estimate to see the credits for each model. Confirm that you have the rights to the files.
Generate and download
Press the generate button with the credit amount. It can take a few minutes; the job keeps running if you close the page. Download the result when it is done.
Other video tools
AI avatar
Make a video of a person talking from one image plus a script or audio file.
5 models · from about 126 credits for 5 s (P-Video Avatar)
Motion control
Copy the movement of a person in a reference video onto the character in your image.
3 models · from about 151 credits for 5 s (P-Video Animate)
Learn moreLip sync
Redraw the mouth in a video of someone talking so it matches new audio or lines.
5 models · from about 46 credits for 5 s (Kling Lip-Sync)
Learn moreStart & end frame
Make a video that moves from a first image to a last image, following your text.
6 models · from about 352 credits for 5 s (Kling 2.6 Pro)
Learn moreExtend a video
Continue a video from its last frame and add the new part to the end.
3 models · from about 805 credits for 5 s (LTX-2.3)
Learn morePlans and credits
- Available on paid plans (Watering, Seed, Feast, Full Course, Team & Business) with an active subscription. Not available on the free plan or during a paid plan's free trial.
- The tools use your studio's monthly AI credits — the same balance you use for novels, manga and video.
- Before generating, you see a credit estimate for the model and length you picked. Nothing is generated until you agree.
- No credits are used if a job fails or if you cancel it before it starts.
Rights and AI disclosure
- Only use images, audio and video that you own or have permission to use. Real people's faces and voices may only be used with that person's permission.
- Do not use the tools to impersonate someone or to make a person appear to say something they did not say.
- The results are AI-generated. When you publish them, label them as AI-generated or AI-edited according to the rules of the platform you post on.
- Model names are listed because you can choose them in the product. Listing them does not imply any partnership with or endorsement by their makers.
FAQ
How long can an AI avatar video be?
It follows the length of the voice: 2 to 30 seconds. Scripts can be up to 300 characters and audio files up to 30 seconds.
Can I use my own photo, or a friend's?
Your own photo, or a photo used with the person's permission, is fine. Photos of real people without their permission are not allowed. You confirm the rights before generating.
Does it work with illustrations or anime-style characters?
Yes, if the image shows one person with a clear face. How well the mouth and face move depends on the art style, so try a low-credit model first.
Can I use my own voice?
Yes. Upload a recording of up to 30 seconds. Speech without music or background noise works best.
How many credits does it use?
It depends on the model and length. For 5 seconds: about 126 with P-Video Avatar and about 438 with Kling Avatar 2.0 Pro (as of October 30, 2026). The estimate shows the exact amount before you generate.
Related
Make it with the studio's video tools
Available on paid plans with an active subscription (not on the free plan or during the free trial). You see a credit estimate before anything is generated.