Turn a single portrait into a singing performance. Upload a photo, add your song, and Solmi drives the mouth, jaw, and head motion to match the vocal so the face actually sings the words. Trim to the hook you want, pick vertical for TikTok and Reels or widescreen for YouTube, and export in 480p or 720p. Works with an MP3 upload, a Suno or YouTube link, or any track you have already made in Solmi.
An AI singing video generator animates a still photo so the face sings a song you supply. Solmi analyses the vocal track, drives the mouth, jaw, and head motion to match it, and renders a finished singing video from a single portrait.
A clear, front-facing portrait with one visible face, even lighting, and no sunglasses or heavy occlusion. Higher-resolution photos hold up better at 720p. You can also run the built-in photo enhancement before generating.
Solmi trims your song to the section you pick, up to 60 seconds per clip. Most creators generate the hook or chorus, then stitch several clips together for a full video.
Singing videos are billed per second of output: 4 credits per second at 480p and 8 credits per second at 720p. A 10-second 480p clip costs 40 credits, and the live estimate updates as you change the trim or quality.
Yes. Upload an MP3 or WAV, paste a Suno, YouTube, or TikTok link, or pick any track you have already generated in Solmi.
Vertical 9:16 for TikTok, Reels, and Shorts, and widescreen 16:9 for YouTube. Pick the ratio before you generate so the face stays framed correctly.