Song Frame
Puts the person from your photo in a vertical scene with a music player card showing a YouTube track's title, then plays that track under the image as a short video.
Overview
Song Frame needs two things: a photo of a person and a YouTube link. Nano Banana, Google's image model, restages the person in a new scene with a translucent music player card in the frame. The card carries the title of the linked video, and the audio from that link becomes the soundtrack of a vertical "now playing" clip.
In the page sample, the woman from the source photo leans against a rain-streaked window at dusk, an earbud in, city lights blurred behind her. The player card floats on the glass with the song title, a progress bar and playback controls. The finished video holds that frame while the first 20 seconds of the linked audio play, or the whole track if it is shorter.
What you can build
- "Now playing" story posts for music, social or dating apps.
- Song-share features that attach a user's own photo to a track they want to post.
- Playlist and listening-party promos that put a fan's face next to a song title.
Inputs
- Input Image: a single photo, uploaded or linked, in JPG, JPEG, PNG, GIF, WebP or HEIC. The default example is a head-and-shoulders portrait of one woman.
- YouTube URL (required): the link to the song. The default points to a music video whose full title shows up on the sample card.
Outputs
A vertical MP4 with sound, 768x1344 in the sample. The page also shows the generated still on its own.
Limitations
- Nothing in the frame moves, so the result plays like a music post with a static cover.
- Every run uses the same scene: the person leans against a wet bus window at night, earbuds in. There is no prompt field to change it.
- The card text is drawn into the image, so small lines can come out wrong. In the sample the title is exact, while the line under it is garbled.
- Audio comes only from a YouTube link, as the app has no upload field for a song file.
Safety & compliance
Get consent from anyone whose photo you use as the portrait. The soundtrack is the audio of the linked video, so make sure you have the rights to use that recording wherever the clip is posted, promos included.
API quick start
Run Song Frame with a single API call.
{
"inputSongUrl": "https://your-cdn.com/input.png",
"inputImage": "https://your-cdn.com/input.png"
}curl -X POST "https://api.wiro.ai/v1/Run/wiro/song-frame" \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_WIRO_API_KEY" \
--data-binary @- <<'JSON'
{
"inputSongUrl": "https://your-cdn.com/input.png",
"inputImage": "https://your-cdn.com/input.png"
}
JSONOther models you might like
Explore similar video generation models.
