Vozmi

Vozmi is a generative video tool that turns a song and a single photo into an AI-made music video. Vozmi generates AI music videos from an uploaded song and a portrait photo, with optional description, lyrics, resolution and aspect ratio settings.

Vozmi is a browser-based AI music video generator that builds a video from two inputs: an audio track and a portrait photo. The creator uploads a song, or picks one already stored in their workspace, then adds a photo of the person who should appear as the performer. The tool animates that image to fit the music and returns a finished clip, which makes it a shortcut for anyone who wants a visual to go with a track without filming anything. The creation form is compact. Audio can be uploaded in MP3, WAV, OGG, M4A, AAC, FLAC or WMA, so most export formats from a music app or DAW are accepted. Beyond the photo upload, a row of sample portraits is shown, which suggests ready-made singers can stand in when no personal photo is available. A free-text description field guides the look of the video, and a Generate ideas button offers help when the creator has no concept in mind. Under More options sit resolution (720p shown by default), aspect ratio (16:9 shown by default), a video title and author name capped at 30 characters each, and a lyrics box. A credit counter beside the Create plan button shows the price of a run, with 20 credits displayed on the page. Finished work is kept under a My creations tab, and an Examples gallery displays sample videos with titles in several languages, including English, Japanese, Spanish and Chinese. That spread hints at use beyond English-language pop. The audience is independent musicians, hobby songwriters, AI-music hobbyists and social creators who need a performance-style video quickly and cheaply. Compared with general text-to-video generators, Vozmi is narrower: it is built around a song and a face rather than free-form scene prompts. It will not replace a directed production with scripted shots, but it covers the common case of a lyric or singer-focused clip. The homepage does not describe pricing tiers, editing controls after generation or export options, so buyers should check those before committing.