💬 Put any words you want spoken in "quotes" to make your image talk — e.g. She smiles and says "Welcome to Sound Genius!"
Your avatars
Generated avatars appear here. These take a few minutes.
Pick one of your tracks, add a photo of the performer, and get a cut, lip-synced music video. Up to 10 minutes.
Clear, front-facing portraits keep the same face across every shot. No photo and the AI invents a performer from the voice.
Looking for full text-to-image with any aspect ratio? Open the AI Image Generator →