Describe a shot and get a short cinematic clip, no camera or footage required. Use it as B-roll in a music video, a teaser for a release, or a looping background for a lyric post.
From a written prompt to an MP4 clip in three steps.
Text to video is for the shots you cannot film: an empty highway at dusk, a crowd seen from above, rain on a window, a slow orbit around a neon sign. Use them as B-roll between performance shots, as a five-second teaser, or as a loop behind lyrics. Draft on Standard, which is silent and takes any length from 1 to 15 seconds, then render the take you keep on Best, which follows a detailed prompt closely and adds generated sound, or on Premium, which adds sound and goes up to 1080p.
A new web account starts with 20 credits. On Standard that pays for one clip of 3 seconds at 720p (20 credits) or 5 seconds at 360p (19 credits). On the free plan the balance tops back up to 10 credits each day you sign in, enough for 2 seconds at 360p. The default Standard clip, 5 seconds at 720p, costs 33 credits. Best costs 12 credits a second, from 60 for 5 seconds, and Premium starts at 48 for 4 seconds at 720p, so both need a paid plan or a credit pack.
A run makes one shot of 15 seconds at most, and 8 on Premium, so it will not cover a full song. It does not take your audio: Standard clips are silent, and the sound on Best and Premium is generated for the scene and does not follow your track. There is no lip-sync, and a new prompt draws a new person each time; to keep a subject, start from a picture with Image to Video or Reference to Video. Words on screen often come out misspelled. Square is on Standard only, and 1080p on Standard and Premium.
New Solmi accounts start with free credits, enough for a first short clip (a few seconds at 720p). After that, each clip costs credits, priced by tier and length and shown before you generate.
Clips are short, typically a few seconds up to about 10 to 15 seconds depending on the tier. For a full-length song, use Solmi's AI music video generator.
Clips render at 720p by default. The Standard tier also offers 360p to 1080p, priced by resolution and length.
Describe the subject, the setting, the camera move, and the mood in one or two sentences.
This tool makes stand-alone clips. Solmi's AI music video generator plans shots to your lyrics and beat and adds lip-sync.