Upload a song as an MP3 or WAV, including one you made in Suno — Solmi's AI music video generator detects the lyrics, syncs visuals to the beat, and renders a finished music video for YouTube, TikTok, Reels, and Shorts. No editing software, no storyboard, no learning curve. Start free.
An AI music video generator (also called an AI music video maker, AI music video creator, or AI MV maker) is a tool that turns an audio track into a finished music video automatically. Solmi analyzes your song, detects beats and lyrics, picks visuals that match the mood, and outputs a video sized for YouTube, TikTok, Instagram Reels, or Shorts — no editing software required.
Yes. Upload the MP3 or WAV (for a Suno song, download it from Suno first; Suno's video download works too). Pasting a Suno share link works only when Suno serves a public file for the song, and Udio links can't be imported, so the uploaded file is the reliable way. Solmi extracts the audio, syncs visuals to the beat, and produces a music video you can publish straight to your social channels.
No. Solmi reads your lyrics and audio to build the visual story for you. You can also describe the look in plain English (e.g. "neon Tokyo at night, anime style") and the AI will follow your direction.
Lyric videos, photo-to-sing performance videos, AI dance videos, cinematic narrative videos, and abstract beat-driven visualizers. Solmi supports cinematic, anime, film noir, pixel art, and dozens of other looks.
Yes, it's free to start with no card on file. A new account on the web gets 100 one-time music-video credits, enough for one 20-second 480p preview of your song with a watermark. Paid plans (from $35/month) render the full song at 720p and 1080p and remove the Solmi watermark.
Optional. Solmi auto-detects lyrics from the audio and renders animated lyric overlays in your chosen style. You can toggle lyrics off for a clean cinematic video or keep them on for TikTok-style lyric videos.
16:9 for YouTube, or 9:16 for TikTok / Reels / Shorts. Pick the format up-front and Solmi renders the visuals safe-zone-correct for that platform.
You do. Videos generated on paid plans are yours to publish, monetize on YouTube/TikTok, and use commercially. See the Solmi terms for full licensing details.
Most songs go from upload to finished video in 3 to 10 minutes, because Solmi renders the shots in parallel. A Studio project where you review the storyboard shot by shot can take longer.
Yes, the audio is all it needs. Upload an MP3, WAV, or M4A of up to 200 MB (or an MP4 or MOV video, and Solmi uses only its audio), and Solmi generates the music video from audio alone, writing the storyboard from the lyrics and beat it detects. A photo is optional: add one and the person in it is cast as the singer, or leave it out and Solmi casts the video for you.
Yes. Add a clear, front-facing photo of yourself as a reference image, and Solmi casts you as the lead singer and lip-syncs you to the vocals. The generator takes up to 3 reference images and casts one person per photo, so a duet needs a photo of each singer. No photo? Pick one of the ready-made singers instead.
Yes. Every video stays saved in the Studio as a project you can reopen, so Solmi works as an AI music video editor too: open any shot to rewrite its description, change its picture, or regenerate just that shot, and the rest of the video is kept. You can also add or restyle the lyric captions. Rewriting a description doesn't use credits; regenerating a picture or a shot does, and the price is shown first.
The free preview has one: it downloads with a Solmi watermark. To get a video without a watermark you need a paid plan (Plus, Creator, or Pro) or a one-time credit pack; either one removes it and unlocks 720p and 1080p.