Video Background Music v2
Writes an instrumental track for a video and mixes it with the clip's own audio. Describe the music in a caption, or leave it empty and the app picks a style from the footage.
Overview
Video Background Music v2 writes an instrumental track for a video you upload and returns the clip as an MP4 with that music in it. Describe the music in plain words, or clear the caption and the app studies the footage and writes a description itself.
By default the new track is mixed with the audio the video already has, so dialogue and room sound stay in the result. Switch the audio mode to replace when you want the music alone. In the alpaca sample on this page, a silent 8-second clip at 2048x1152 comes back at the same length and resolution with a stereo music track added.
What you can build
- Background music for silent product clips and AI-generated footage
- A "make it sound like this song" option, with an uploaded track as the style reference
- Music at a set tempo for edits cut to a beat
- A fresh soundtrack in place of noisy camera audio
Inputs
- Video (required): one file or URL, in MP4, WEBM or MOV.
- Caption: free text about the music, such as a genre and the instruments you want. The default is "Classical piano music." Leave it empty to have the video analyzed instead.
- Reference audio: one optional song in MP3, WAV, M4A, WEBM or OPUS, used as style inspiration.
- Audio mode: mix (default) keeps the video's own sound under the music; replace drops it. A video without sound always gets the music alone.
- BPM: 0 to 300. At 0 the app picks the tempo. The form suggests about 80 for a slow ballad and 128 for dance.
- Background music volume: 0.1 to 2, default 0.7. It sets the music level.
- Original volume: 0 to 500 percent, default 100. In mix mode it sets the level of the video's own sound; 0 silences it.
- Seed: 0 to 9999999, default 42.
Outputs
One MP4: the original video with the generated instrumental in its soundtrack, mixed with or in place of the original sound.
Recommended settings
Run once with an empty caption to hear what the analysis picks, then write a caption when you want a specific genre or instrument. On clips with dialogue, keep mix mode and lower the music volume below 0.7 if it competes with the voices, or lower the original volume to push the music forward. When both are loud at once the result can clip, so bring one of them down. A new seed gives a different take on the same settings.
Limitations
- The music is instrumental, with no vocals or lyrics.
- The automatic description can miss the tone you had in mind. A written caption gives you more control.
API quick start
Run video-background-music-v2 with a single API call.
{
"inputVideo": "https://your-cdn.com/input.mp4",
"caption": "Classical piano music.",
"audioMode": "mix",
"inputAudio": "https://your-cdn.com/input.mp3"
}curl -X POST "https://api.wiro.ai/v1/Run/wiro/video-background-music-v2" \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_WIRO_API_KEY" \
--data-binary @- <<'JSON'
{
"inputVideo": "https://your-cdn.com/input.mp4",
"caption": "Classical piano music.",
"audioMode": "mix",
"inputAudio": "https://your-cdn.com/input.mp3"
}
JSONOther models you might like
Explore similar video generation models.
