Music video director
Plan every shot, then film it to your song
Music Video Director turns one song into a timed shot list (30 seconds by default), with each shot's picture, camera move, and lyric line, plus a key visual and opening and closing titles. From that plan it makes storyboard frames, brings each frame to motion, and joins the clips over your song with lyric captions in a video of up to two minutes, or makes a photo sing an excerpt. Music Video Director works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Music Video Director and tell me when I need to sign in: https://beatra.ai/skills/music-video-director/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.Docs ↗

One song, one music video
The shot list comes first
Concept, timed shots, key visual, and opening and closing titles arrive in the first reply.
Cut to your song
Each frame becomes a clip, and the clips play over your song with titles and lyric captions.
A photo that sings
Your photo sings a line of the song, in the photo's own shape.
How it is made
Every shot on paper
A 30-second shot list in timed segments, a key visual, and the opening and closing titles.
Timecode and picture for each shot · Camera move for each shot · The lyric line sung over it
Frames, then clips set to the song
One frame per shot in the video's shape, then each frame in motion, joined over your song in a video of up to two minutes.
A photo that sings, or a new song
A portrait lip-syncing a line of the song, or a company, wedding, or anniversary song written from your words.
Songs that need a video
Original songs
Give a song you wrote its first music video.
Company songs
Write the company or hospital song, then make its video.
Weddings and anniversaries
A song for the day, with a video from your own photos.
Song teasers
A chorus-length music video for the release post.
Inputs and outputs
Input · Text — The song's title, lyrics, and mood
Input · Audio — The song, or the excerpt to film
- Formats
- MP3
Input · Image — A photo to sing an excerpt (optional)
- Formats
- JPG, PNG
- Specifications
- 1 image per request
Output · Text — MV concept, a timed shot list, key visual, and opening and closing titles
- Specifications
- editable
Output · Image — Storyboard frames and the key visual
- Specifications
- 2K; aspect ratios 16:9, 9:16, 1:1, 3:4
Output · Video — Music video joined over your song with lyric captions
- Formats
- MP4
- Specifications
- up to 120 s; 1080p; aspect ratios 16:9, 9:16, 1:1, 3:4
Output · Video — Lip-sync singing clip from a photo
- Formats
- MP4
- Specifications
- up to 15 s
Output · Audio — A new song with vocals from your lyrics (optional)
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Text — The song's title, lyrics, and mood | — | — |
| Input | Audio — The song, or the excerpt to film | MP3 | — |
| Input | Image — A photo to sing an excerpt (optional) | JPG, PNG | 1 image per request |
| Output | Text — MV concept, a timed shot list, key visual, and opening and closing titles | — | editable |
| Output | Image — Storyboard frames and the key visual | — | 2K; aspect ratios 16:9, 9:16, 1:1, 3:4 |
| Output | Video — Music video joined over your song with lyric captions | MP4 | up to 120 s; 1080p; aspect ratios 16:9, 9:16, 1:1, 3:4 |
| Output | Video — Lip-sync singing clip from a photo | MP4 | up to 15 s |
| Output | Audio — A new song with vocals from your lyrics (optional) | — | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What do I start with?
The song: its lyrics, what it is about, or the finished track. Add the length and where it will be posted if you know.
Does the video play my song?
Yes. The clips are joined over your song from its first second, with the titles and lyric lines on screen. Send the chorus as its own file to set the chorus under the video.
Can a photo sing?
Yes. A portrait photo sings an excerpt of up to 15 seconds, its mouth moving with the words, in the same shape as the photo.
How long can the video be?
Up to two minutes in one video. A longer song is made as its chorus or strongest section, or as several parts.
Related Skills



