AI Avatar Video

Daily check-in: 15 free credits

AI Avatar Video Generator

An AI avatar video is a talking presenter made from one portrait photo: Kling AI Avatar animates the face so it speaks your typed script or your own recording with lip sync. Videos run as long as the speech, up to 5 minutes, in 9:16, 16:9 or 1:1, with optional burned-in captions. Avatar videos use purchased credits.

Use only a photo of yourself or of a person who agreed to it.

0 / 3,500 characters

Your own cloned voices from B-roll Cut show at the top of the list.

Adds subtitles to the picture. You also get SRT and VTT files.

Make the voiceover first. The video price depends on its length.

AI avatar videos use purchased credits. Free credits pay for Z-Image, video templates and Code to Video only.

Upload a portrait to start.

Your talking presenter video shows here. Upload a portrait and add the speech to start.

How the AI avatar video generator works

  1. 1

    Upload a portrait

    Pick a clear, front-facing JPEG or PNG photo of one person. Choose a vertical, wide or square frame.

  2. 2

    Add the speech

    Type a script and pick an AI voice or your own cloned voice, or upload an MP3, WAV or M4A recording of up to 5 minutes.

  3. 3

    Make the avatar video

    Kling AI Avatar animates the face so the lips, eyes and head move with the speech. Add captions if you want them.

  4. 4

    Download and share

    Watch the talking video on the page, download the MP4, SRT and VTT files, and share it. Every video is saved in My Works.

What people make with AI avatar videos

Faceless social media channels

Post TikTok, Reels and Shorts with a steady on-screen presenter, without filming yourself every day.

Product explainers and ads

Let a presenter walk through a product, a feature or an offer, and update the script when the offer changes.

Courses and onboarding

Turn lesson scripts into talking head videos that are easy to fix later: change the text and make a new take.

Multilingual messages

Write the script in another language and the same avatar speaks it, with captions in that language.

More video tools

A Guide to AI Avatar Videos

What an AI Avatar Video Is

An AI avatar video is a talking presenter made from a still photo. The AI reads the speech, predicts how the mouth, jaw, eyes and head move for every sound, and animates the face of the photo to match. The result looks like a person who speaks to the camera.

This generator uses Kling AI Avatar. The video is exactly as long as the speech, up to 5 minutes, so one photo can carry a 15 second ad or a full lesson.

How to Pick a Good Portrait

Use a sharp photo of one person who looks at the camera, with the face well lit and not covered by hands, hair or sunglasses. A neutral or slightly smiling mouth gives the most natural lip sync.

The photo is cropped to the frame you choose before the video is made, so leave some space above the head and around the shoulders. A vertical frame suits TikTok, Reels and Shorts; a wide frame suits YouTube and websites; a square frame suits feeds.

Script or Recording: Which One to Use

Type a script when you want a clean studio voice. You hear the voiceover first and pay for the video only when you like it. Pick one of the AI voices, or your own voice if you cloned it in B-roll Cut.

Upload a recording when the speech must be your real voice or a voice actor's. Clear speech without loud music gives the best lip sync. The price is set by the length of the recording, which the server reads from the file.

Captions for Silent Viewing

Most short videos are watched without sound. Burned-in captions put the words into the picture, so every viewer can follow the presenter. A typed script uses its own timing for the captions; a recording is transcribed first.

You also get the captions as SRT and VTT files, which YouTube and most players accept as a separate track. To reach another language later, run the finished video through the Video Translator.

Use Faces Responsibly

Make avatar videos only of yourself or of people who gave you their permission. Do not use a photo of a public figure or a private person to make them say something they did not say.

Tell your viewers when a presenter is AI generated if the platform or your audience expects it. Clear labels keep trust in your channel and follow the rules of most social platforms.

AI Avatar Video FAQ

What do I need to make an AI avatar video?
One portrait photo (JPEG or PNG, up to 10 MB after cropping) and the speech: a typed script read by an AI voice, or your own MP3, WAV or M4A recording of up to 5 minutes.
How long can the video be?
As long as the speech, from 1 second to 5 minutes. A typed script can have up to 3,500 characters.
How much does an avatar video cost?
The price depends on the length of the speech and the quality. Standard 720p costs about 4 credits a second, Pro 1080p about 8 credits a second, and captions add a little. The page shows the exact price before you start.
Can I use free credits?
No. AI avatar videos use purchased credits. Free credits pay for Z-Image, video templates and Code to Video only. If a video fails, the credits go back to your balance.
Can the avatar speak with my own voice?
Yes. Upload a recording of your voice, or clone your voice once in B-roll Cut and pick it from the voice list when you type a script.
Which languages does it support?
The lip sync follows the sound, so it works for any language that the voice speaks. The AI voices handle English, Chinese, Spanish, Japanese and many more.
Which frame sizes can I choose?
Vertical 9:16 for TikTok, Reels and Shorts, wide 16:9 for YouTube, and square 1:1 for feeds. The photo is cropped to the frame before the video is made.
Where are my videos saved?
Every finished video is saved in My Works, where you can watch it again, download it and share a link to it.