Can I create a full-body avatar?

Yes! Just upload a full-body photo or video that meets our quality requirements (resolution, size, format, etc.).

What should I avoid in my photo or video?

Avoid face obstructions (especially the mouth), extreme head tilts (over 45°), or other people in the frame.

Can I use an AI-generated photo?

Yes, as long as it’s a clear JPG or PNG (max 10MB, 1080P), with a single, visible face—no mouth covered, and head tilted under 45°.

What photo formats are supported?

JPG or PNG, up to 10MB, with resolution of 1920×1080 or 1080×1920.

Can I use a photo without uploading a voice clip?

No. A 5–10 second voice clip is required with a photo. If you don’t have one, you can use a preset voice, but that voice will be used in your avatar’s videos. For the best results, we recommend recording your own in a quiet space.

Why do you need an audio clip for photo-based avatars?

To clone your voice, we need at least 5 seconds of clear, natural speech. You can also choose a default voice instead.

What video formats are supported?

MP4 or MOV. Recommended resolution: 1080p–4K. Max file size: 1GB. If the video’s too long, we’ll auto-trim it to a 1-minute preview so you can select your 5-second clip.

Why do you only use a 5-second video clip?

We use a short, natural speaking clip to speed up avatar creation and give you a smoother experience. Choose a clip that feels conversational.

Can I request specific movements for my avatar?

Not at this stage. To keep things fast and simple, we only support basic expressions based on your video. For custom actions, contact us about advanced options.

Can I change the avatar’s background or make it transparent?

No, background replacement isn’t supported. Please record your video with the background you want to appear in the final output.

Does the training video need to include audio?

No. If no audio is detected, we’ll ask you to upload or record one, or you can pick a default voice from our library.

Can I use a singing clip as my audio?

No. Since the avatar is used for natural speech, we need a voice clip with regular spoken language.

How long does avatar training take?

About 15–20 minutes with a stable internet connection.

Where can I check my avatar’s status?

In your [Avatar Library - Personal] section.