Can Music Video Maker use my own photos?

Music Video Maker generates its scene images from the audio context and chosen photo style. For a manually arranged background and timeline, open the Music Visualizer Editor.

Which aspect ratios can I export?

Music Video Maker renders either 16:9 or 9:16. Each generation produces one MP4 in the selected shape; square output is not offered in this form.

How much control do I have over captions?

Caption settings include an on/off toggle, a style preset and top, middle or bottom alignment. These settings are included in the rendered video; changing a completed export requires another render.

Is Music Video Maker free to generate?

Audio preview and quote review use no generation credits. Image creation and video rendering require the displayed credit amount, which you confirm before starting.

What quality and upload limits should I check?

Music Video Maker accepts supported audio up to 50 MB, and a story video covers up to 5 minutes of song (30 scenes); trim a longer song first. Review automatic words and images before sharing, and use only material you have permission to publish.

How many credits does Music Video Maker use?

Music Video Maker draws between 39 and 318 credits per run, depending on the settings selected in the form.

Music Video Maker: Audio to MP4

Music Video Maker

Video audio

Drop your audio here or choose a file

MP3, WAV, OGG, M4A, AAC and FLAC where supported by your browser. Up to 50 MB and 15 minutes.

Make

Every scene's picture and its AI clip in one run, cut together on your song.

Video size

Clip quality

Clip model

Natural motion at the lowest price per clip.

Characters

Locations

Photo style

Visual direction

Use my scene prompts

Captions and sound wave

Enable lyrics

No captions yet. Use the song's captions, import an LRC file, or run Auto captions below.

Caption style

Caption alignment

Show sound wave

Each character and location is drawn once as a reference picture (9 credits each), and every scene it appears in is drawn from it, so faces and places stay the same across the video.

Each scene becomes an AI video clip of up to 8 seconds made from its own picture, cut where your lyric lines fall and on the beat, under your captions. Check the price before starting.

Audio and caption preview

Choose audio to preview timing and caption placement. Generated story videos appear in My videos.

1.Choose your song
Upload it, record it or pick one from My music. The scenes follow its length.
2.Set the story
Recurring characters and places, a photo style and a clip model, or Storyboard first to review the pictures before any clip.
3.Check the price and generate
Each scene becomes an AI clip cut on the beat under your captions. Edit or redo any scene later in the editor.

Example

Made here: a woman with an umbrella on a rainy neon street, two scenes animated into AI clips and cut to the song.

Upload audio or choose My MusicLandscape or portrait outputAn AI video clip of up to 8 seconds per sceneCaption style and position controlsReview credits before generation

Exports from the music video renderer

The first clip is a story video made on this page from an 8-second melody: two AI scenes, each animated into its own clip, cut together under the sound wave. The others come from the same renderer, drawn in its sound wave styles without the generated scenes your own video adds; each is a 45-second 720p excerpt with captions off because the tracks have no timed lyric lines.

Built For Creators

Who needs a video around a finished track

YouTube Podcasters

Give a short spoken recording on-screen captions and a waveform for a video upload.

DJ Set YouTubers

Turn an excerpt from a mix into generated scenery with audio-reactive movement.

Independent Artists

Pair a finished single with AI imagery and styled lyrics for a visual release.

How to use Music Video Maker

Choose the finished recording

Upload a supported audio file or choose a song you own in My Music. The video uses this track for its full duration.

Arrange the visual treatment

Choose 16:9 or 9:16, a clip quality (720p or 1080p) and a photo style. Set caption placement and whether to display the sound wave.

Check the quote and generate

Review the displayed credits, confirm generation and follow the task in My videos. Download the completed MP4 for review and sharing.

Music Video Maker controls

Music Video Maker builds a visual release around a finished recording. Upload audio or select your own My Music track, then choose generated imagery, captions and a waveform for the MP4.

Sound designer analyzing BPM key and pitch before editing audio

Scenes that move with the song

AI plans the scenes from your lyrics, draws each one with the same main character, and animates it into a video clip of up to 8 seconds. Each cut falls where a lyric line starts or between lines, then on the beat.

One composition in your chosen shape

Select a wide canvas for a landscape video or a tall canvas for a vertical release. Changing settings requires a fresh quote before submission.

Text and audio movement

Caption presets control the look of transcribed words. The optional waveform responds to the recording, independently of the caption toggle.

What goes into one music video

Audio in, two aspect ratios out

Up to 8 seconds of AI video per scene

Each scene's picture becomes a moving shot, cut where the lyric lines fall.

30 scenes at most

Covers up to 5 minutes of song; trim a longer one first.

2 aspect ratios

16:9 for YouTube and 9:16 for vertical feeds.

6 upload formats

MP3, WAV, OGG, M4A, FLAC and AAC.

Where Music Video Maker results go next

AI Music Generator

AI Mastering

AI Music Visualizer

Music Video: Visualizer

AI Music Video

Music Video Maker questions

Understand the source, render settings and review steps for your finished music video.

Build a visual release around your recording

Choose how the recording appears on screen, then check the generation price.

Open Music Video Maker Explore video tools