AI Lip Sync: Your Portrait Gives a Wordless Greeting

Choose one of the two scene chips, upload one photo of an adult who has agreed to appear, and generate the clip. The result is a 15-second, 16:9 portrait video with environmental sound and instrumental music. It contains no human voice, and you cannot upload your own audio. The scene choice sets the background for the person in your photo.

No. This page creates a portrait video with a soundtrack, but the soundtrack has no dialogue or human voice. The person in the photo does not deliver a line or sing, so the photo does not appear to speak. Choose a scene for the visual setup.

No. The tool does not accept your own song, voice recording, or other custom audio. Each generated clip uses environmental sound and instrumental music, with no human voice. Choose a scene chip and one photo to make the preset wordless portrait video.

There are two scene chips: Talking Portrait and Friendly Greeting. Talking Portrait uses a warmly lit street food stall, lanterns, and a softly blurred rainy alley; Friendly Greeting uses a clean, softly lit neutral background with head-and-shoulders framing. You cannot enter a custom scene description. The photo greeting video uses the scene you select, and the wordless talking portrait has no spoken voice.

Each generated video is 15 seconds long and uses a 16:9 aspect ratio. You cannot set a different duration or choose another aspect ratio on this page. The soundtrack contains environmental sound and instrumental music, but no human voice.

Upload one clear photo of yourself or an adult who has agreed to appear. A portrait that clearly shows the person gives the scene a straightforward visual reference. This page takes one photo per video, so it cannot use a second image or combine multiple people from separate photos. The selected scene supplies the background and framing for the 15-second clip.

No. The Friendly Greeting chip describes the visual scene, not a spoken message. The video includes instrumental music and environmental sound without human speech, and you cannot upload a recording or type words for the person to say. Use it as a wordless visual greeting.

Check the current price and credit options on the pricing page before you generate. The available options and amounts are listed there.

Start with one photo of an adult who has agreed to appear, select one of the available scene chips, and check the result before sharing. This page makes a 15-second, 16:9 clip with instrumental music and environmental sound, without speech or custom audio. Read the AI trend video guide for general guidance on preparing and sharing a trend clip.