Back to home

About AI Music Visual

Learn how AI Music Visual turns a portrait and your audio into a singing video, and where to find product, account, and billing support.

Last updated: 2026-11-18

About the workspace

AI Music Visual is a browser workspace for creating singing videos from a portrait and an audio clip. Upload a clear photo of a person and a song or vocal recording in the music video workspace, then generate a lip-synced performance.

From your recording to a video

The current workflow uses one portrait and an MP3, WAV, or M4A audio file. Prepare the excerpt you want before uploading: the uploaded audio sets the video length. The photo provides the person, setting, and framing, without a scene prompt or multiple reference images.

Choose a resolution and review the credit cost before generating. The result panel shows task progress and lets you preview and download a completed video. You can also find saved results in My Assets. See Pricing for plans and Credit Packs.

Your music and your permissions

Use recordings and photos you own or have permission to use. This includes rights in the song, recording, voice, and the likeness of any person shown. A generated video or a paid plan does not grant permission to use someone else's music or identity.

AI Music Visual is independent of Suno and the developers of the AI models it uses. Model and product names do not imply an official relationship or endorsement. Suno accounts and Visual credits are separate from AI Music Visual accounts and credits.

Policies

Contact

Email support@aimusicvisual.com or use account support for product, account, or billing questions.