Black Friday sale· 50% off first month
Cover for the guide on making an AI avatar video from a photo
Characters

Official BytePlus partnerBytePlus, a ByteDance company

How to make an AI avatar video from one photo

Make an AI avatar video: one photo plus a script or a recording gives a presenter that speaks to camera. Takes of 4 seconds to 5 minutes. Steps, cost and tips.

KreatorFlow4 min read

Short answer

Open Lip Sync, add one clear photo of your presenter, then give it a voice: type a script and pick a voice, or upload an audio file. Press generate and the photo speaks the script. One take runs 4 seconds to 5 minutes. It costs 4 credits per second of audio at 720p and 6 at 1080p. Lip Sync needs a paid plan or a credit pack (packs start at $8).

Updated:

Make an avatar video in five steps

  1. 1

    Choose the face

    Use a sharp photo with one face, the mouth uncovered, head and shoulders or half body. It can be you, someone who agreed, or a person you made in the AI character generator. Save it as a character to reuse the same face.

  2. 2

    Write the script for the ear

    Short sentences and natural pauses sound better than long paragraphs. Read it out loud once before you use it.

  3. 3

    Give the avatar a voice

    Type the script and pick a voice (the line costs 2 credits per 1,000 characters), or upload your own recording. MP3 or WAV under 15 MB, from 4 seconds to 5 minutes long.

  4. 4

    Add a short direction, only if you want one

    One or two sentences about camera and mood are enough, such as a slow push-in and a smile at the end. Do not describe what is already in the photo.

  5. 5

    Pick a size and generate

    Test at 720p, then make the final at 1080p. The studio shows the exact cost for your track before anything is charged. If a job fails, the credits come back.

What an AI avatar video is

An avatar video is a still photo that talks. You supply the face and the words, and the video shows that face speaking them, with lips, expressions and head movement that follow the voice.

It makes one continuous talking shot from one photo. It does not make a live avatar, and it does not film new scenes around the presenter. Add your own b-roll or screen recording in an editor.

Keep the same avatar in every video

Use the same photo each time and the same voice. Design the face once in the character generator, save it, and pick it in Lip Sync for each episode.

For a voice that stays the same, use one of our voices, or clone your own voice once in the Audio studio and make each line there. Only clone your own voice or one you have written permission to use.

Long scripts

One take can be up to 5 minutes. For a longer video, make several takes and join them in an editor. Several shorter takes with a cut between them also look more like real editing than one long shot.

Rights and honesty

Use a photo of yourself, of someone who agreed, or of an AI-generated person, and a voice you have the right to use. Label an AI presenter as AI-generated where a platform asks for it.

Do not present an avatar as a real customer or a real expert.

Frequently asked questions

How do I make an AI avatar video?

Open Lip Sync, add one clear photo of your presenter, then give it a voice: type a script and pick a voice, or upload an audio file. Press generate and the photo speaks the script. One take runs 4 seconds to 5 minutes. It costs 4 credits per second of audio at 720p and 6 at 1080p. Lip Sync needs a paid plan or a credit pack (packs start at $8).

How long can an avatar video be?

One take is 4 seconds to 5 minutes. The video is as long as the audio.

How much does it cost?

4 credits per second of audio at 720p and 6 at 1080p. A one-minute video costs 240 credits at 720p, plus 2 credits per 1,000 characters if you type the script and use one of our voices. The studio shows the exact cost for your track before anything is charged.

Can I use my own voice?

Yes. Upload a recording of yourself. MP3 or WAV under 15 MB, from 4 seconds to 5 minutes long. You can also clone your voice in the Audio studio and make the lines there.

Can the avatar hold or show my product?

Lip Sync animates the person in the photo and does not add new objects. If the product should be in the shot, put it in the photo first.

Can the avatar speak another language?

Yes. The lips follow the audio. Make the line in another language in the Audio studio, or upload a recording, and use the same photo for each version.

Make your first avatar video

Add a photo and a script and see the price first. Lip Sync needs a paid plan or a credit pack (packs start at $8).

More guides