What is Suno AI Video?
Suno AI Video generates a short video that plays over a part of a song. The song is a Suno clip, sent as clip_id, and its audio drives the video. You describe the picture in prompt, set a duration of 5 to 10 seconds, and choose where the segment starts with clip_start_time, so a 10-second video starting at 42 covers seconds 42 to 52 of the track. Each request returns two videos. You can pin the opening or closing shot with a first-frame or last-frame image, either from a URL or from a Cover Art result. Two quality tiers are available: basic for speed and cost, advanced for more detail. This is a generated clip for a slice of the song. For a full-length video that plays the song over its artwork, use Music Video instead.
Key features of Suno AI Video
Six request fields cover most of the control you get.
Pick the song segment
clip_start_time sets where in the song the video starts, and duration sets how long it runs, from 5 to 10 seconds. Point it at the chorus or the drop.
Optional first and last frames
Pass start_image_url and end_image_url, or the IDs of Cover Art images, to fix how the video opens and closes. Frames are optional on both ends.
Two videos per request
The finished task returns a videos array with two results, each with a hosted url and a thumbnail_url, so you can choose the better one.
Basic and Advanced quality
basic is the default and suits drafts and high-volume use. advanced gives more detail for the version you publish.
Square, wide or vertical
aspect_ratio defaults to 1:1. Use 16:9 for landscape players and 9:16 for vertical short-form feeds.
Best for
Chorus clips for promotion
Set clip_start_time to the hook and render a 9:16 video for short-form platforms before a release.
Release teasers
Generate a few 5-second clips from different parts of a song and cut them into a teaser.
Loops for live visuals
Use the same image as first and last frame to help the clip loop behind a live set or a stream.
Visuals that match the cover
Pass a Cover Art image ID as the first frame so the video starts from the release artwork.
Canvas-style background video
Make a short square or vertical clip to play behind a track in a player or on a profile page.
Use cases
A music app can add a "make a video" button that sends the current song, the timestamp the user is listening at as clip_start_time, and a short prompt, then shows both videos for the user to pick. A release tool can generate artwork with the Suno Cover Art API and pass the chosen image ID as start_image_id, so the promo clip opens on the cover. If the goal is a video of the entire song rather than a generated scene, the Suno Music Video API renders the full track over its artwork as an MP4.
API examples
Full parameter docs are at docs.unifically.com/models/audio/suno/video-gen.
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "suno-ai/video-gen",
"input": {
"clip_id": "1901ec96-72c6-4c26-8e56-91028ca6070d",
"prompt": "slow dolly through a rain-soaked neon street",
"quality": "basic",
"duration": 10,
"clip_start_time": 42,
"aspect_ratio": "9:16",
"start_image_url": "https://example.com/first-frame.jpg"
}
}'
The request returns a task_id. Poll GET /v1/tasks/<task_id> until the videos array is ready, or include a callback_url so the result is posted to your server.
FAQs
People also ask
Short AI-generated videos for a segment of a song. You send the song's clip_id and a prompt, and the finished task returns two videos in a videos array, each with an id, a hosted url and a thumbnail_url.
5 to 10 seconds, set with duration. The default is 10.
Set clip_start_time to the second where the segment should start. The segment ends duration seconds later. The default is 0, the start of the song.
No. You can give a start frame, an end frame, both or neither. Use start_image_url and end_image_url for hosted images, or start_image_id and end_image_id for images from a Cover Art result. Use one form per frame, not both.
Set it with quality. basic, the default, is tuned for speed and cost. advanced is tuned for quality and detail and is billed at a higher per-second rate.
Per second of video, at a rate that depends on the quality tier. Check the pricing page for current rates. Prompts and frames go through content moderation, and a rejected request fails with the reasons in the task error instead of being charged.
