🎬 Video and Music Mix

Join your clips and photos into one video and lay a track over it

About this tool

Turn a handful of clips and photos plus one song into a single video. Drop your MP4 clips and your JPG/PNG pictures (or add an AI image from a prompt), drag them into order and give each picture a length in seconds. The first clip or picture sets the format and everything else is scaled to cover and centre-cropped, so nothing looks stretched. Add the music, see at a glance whether the picture or the song is longer, and choose what happens at the end: hold the last picture, fill the rest with a colour, or fade the music out. If a clip has its own sound it is mixed with the music, each side with its own volume. Preview three seconds of the mix, then render the whole video with the sound baked in. Free, no signup, no watermark.

Drop your clips (MP4) and pictures (JPG/PNG), or add an AI image from a prompt. Drag to reorder. Pictures show for 3 seconds by default.

Your clips and images *

Sequence

⬆ Drag & drop videos (MP4) and pictures (JPG/PNG) here

Total length: 0.0 s

Videos play in full. Pictures run for the number of seconds you set (3 by default). The first item sets the format.

Add the track. The picture length is shown next to the music length, with the options to match them. You can also delay the music, so the video opens with clean dialogue before the track comes in.

Music *

⬆ Drag & drop a file here

MP3 or WAV. The video follows this track's length.

Picture vs music

Add your clips and music to see the lengths.

Music start offset (seconds of silence)

Leave it at 0 to start the music straight away. Enter 5 and the track comes in after 5 seconds of silence - the whole video is that much longer, so you get a clean opening (dialogue, ambience, a product shot) before the music starts.

End of the video

Auto-match holds the last image (or freezes the last frame of a video) so the picture reaches the end of the music, and trims the video when it is the longer one.

Fade out length (seconds)

How long the music takes to fade at the end.

Background colour

#000000

The colour that fills the time the picture does not cover.

Set the volume of the video sound and of the music, preview 3 seconds, then render.

Video sound volume %

100

0 % mutes the sound that comes with the clips. 100 % is unchanged.

Music volume %

100

100 % is the track as it is.

Preview the mix

Renders the first 3 seconds of the mix (audio only, so it is quick).

Output size

Frame rate

API

POST /api/tools/video-music-mix/run (multipart/form-data) → JSON with outputs[].url, a zip link and a config_url.

Every run also hands you the config JSON (button above). It is the request body - POST it straight back to replay the exact generation:

curl -X POST -H 'Content-Type: application/json' \\
  --data @genbox-config-video-music-mix.json \\
  /api/tools/video-music-mix/run

For AI agents · API specs

Technical specs

Category	video
Slug	`video-music-mix`
Run endpoint	`POST /api/tools/video-music-mix/run`
Content type	`multipart/form-data` (with file uploads) or `application/json`
Response	JSON: `job`, `notes`, `outputs[].url`, `zip`, `config_url`
Rate limit	API: 1 request / minute / IP. Live preview and image renders have their own separate limits, plus a short global cooldown between renders (storm protection). Over a limit you get HTTP `429` + a `Retry-After` header (local requests are unlimited)
Machine-readable spec	`GET /api/tools/video-music-mix`
OpenAPI 3.1 (Swagger)	this tool (JSON) · all tools

Request body

Every parameter accepted by the run endpoint, in request-body order. Fields are optional unless marked required. The same schema is published as OpenAPI 3.1. Upload files with multipart/form-data; a JSON body replays a saved config.

Parameter	Type	Required	Default / allowed values	Description
`sequence`	sequence	required		Videos play in full. Pictures run for the number of seconds you set (3 by default). The first item sets the format.
`audio`	file	required		MP3 or WAV. The video follows this track's length.
`mixinfo`	mixinfo	no
`music_offset`	number	no	`0`	Leave it at 0 to start the music straight away. Enter 5 and the track comes in after 5 seconds of silence - the whole video is that much longer, so you get a clean opening (dialogue, ambience, a product shot) before the music starts.
`fit_mode`	select	no	`auto` · `color` · `fadeout` · `silent`	Auto-match holds the last image (or freezes the last frame of a video) so the picture reaches the end of the music, and trims the video when it is the longer one.
`fade_seconds`	number	no	`2`	How long the music takes to fade at the end. Only used when `{"fit_mode": ["fadeout"]}` matches.
`background_color`	color	no	`#000000`	The colour that fills the time the picture does not cover. Only used when `{"fit_mode": ["color"]}` matches.
`video_volume`	range	no	`100`	0 % mutes the sound that comes with the clips. 100 % is unchanged.
`music_volume`	range	no	`100`	100 % is the track as it is.
`preview_mix`	mixpreview	no		Renders the first 3 seconds of the mix (audio only, so it is quick).
`resolution`	select	no	`auto` · `1920x1080` · `1280x720` · `1080x1920` · `720x1280` · `1080x1080`
`fps`	select	no	`24` · `25` · `30`

Call it from an agent

GET /api/tools/video-music-mix - machine-readable spec of this tool (inputs, category, API block).
GET /api/tools - list of every tool plus the categories.
POST /api/tools/video-music-mix/run - run it. Accepts multipart/form-data (with files) or a raw application/json body. Returns JSON with outputs[].url, zip and config_url.
The config_url JSON is the request body - POST it back to replay the same generation.

# agent example
curl -s https://genbox.eu/api/tools/video-music-mix/run \\
  -H 'Content-Type: application/json' \\
  --data @genbox-config-video-music-mix.json

Rate limits

Max 1 request per minute per IP on the run endpoint.
Over the limit you get HTTP 429 with retry_after (seconds) - wait that long and retry.
Higher limits and API keys are coming soon: an API key will lift the per-IP throttle. Not available yet.