Video Brief Template: How to Brief Your AI Music Video Director
A brief for an AI music video director is one page answering five things: the song, the visual style, who or what recurs on screen, what happens across each song section, and the hard rules the video must never break. Write it before you open the app, then paste it into the box where you describe your idea. In Melodious the director listens to your song first, then asks which part to make, who is on screen and whether to lip sync, so your brief answers the creative questions it does not ask and gives the three ideas something specific to work from. Your photo or character is used as the reference for every frame. The template below is fill-in-the-blank with a worked example underneath. Copy it, spend fifteen minutes on it, and you'll spend far less time redoing scenes that weren't wrong, just never specified.
Plans from $29/month, cancel anytime. Starter makes a 30-second video with lip sync a month.
What goes in a brief for an AI music video director?
The short answer: A brief for an AI music video director is one page answering five things: the song, the visual style, who or what recurs on screen, what happens across each song section, and the hard rules the video must never break. Write it before you open the app, then paste it into the box where you describe your idea. In Melodious the director listens to your song first, then asks which part to make, who is on screen and whether to lip sync, so your brief answers the creative questions it does not ask and gives the three ideas something specific to work from. Your photo or character is used as the reference for every frame. The template below is fill-in-the-blank with a worked example underneath. Copy it, spend fifteen minutes on it, and you'll spend far less time redoing scenes that weren't wrong, just never specified.
Almost every disappointing AI music video traces back to the same moment: someone typed "make it cinematic and moody" into the box and pressed enter. The model did exactly that. It produced a competent video about nothing in particular, because nothing in particular was asked for.
A human director would have interrogated you first. What city? What time of night? Who's in it? What are we never showing? The Melodious director does ask a few questions, but they are about the song and the casting, not the look, so the creative interrogation has to happen on paper, before you start. That's all a brief is, the questions a director would have asked, answered in advance. If you're new to the end-to-end process, how to make an AI music video covers the full flow; this post is the fifteen minutes that happen before step one.
In a hurry? Jump straight to the template — the worked example is directly underneath it.
Prepare the song before you write a word of the brief
The brief describes what happens over a song, so the song has to be settled first.
- Export a real audio file. MP3, WAV, M4A, AAC, OGG and FLAC all upload, up to 50 MB. Check the exported file is under 50 MB: WAV size depends on sample rate and bit depth, and a long uncompressed session bounce can easily exceed it.
- Upload the mix you'd release, not the rough. Tempo, sections and the vocal are read off the file you give it. A phone-recorded demo produces a fuzzier structural map, and the storyboard is built on that map.
- Decide which part of the song this video is. The director's first question is which part to make, from a short part up to the full song, and a video can be up to 5 minutes long. Everything after that question covers only the part you pick. If you're making 60 seconds of a 4-minute track, know which 60 seconds before you start, usually a chorus into a bridge, not the intro.
- Check the vocal sits up in the mix. The director reads the lyric lines and their timing from the vocal to place lip-synced shots, so a buried vocal is harder to read than a present one. Melodious does not put lyrics on screen; for that, see the lyric video guide.
- Reuse a song you added before. Choose from my assets in the + menu lists the songs and characters you have used before, so second and third videos on the same track skip the upload.
The video brief template
Copy this whole block. Every line is either a blank or a choice between named options.
# MUSIC VIDEO BRIEF — [song title]
## 1. THE SONG
Track: [title + the exact section, if you're cutting it down]
Part: [hook / chorus / verse + chorus / full song, up to 5 minutes]
Feel: [tempo and genre in five words]
Lyric images: [two or three concrete nouns lifted from the lyrics]
Faces on screen: [yes / no, if yes, decide who sings; lip-synced shots cost more]
## 2. THE LOOK
Style: [moody cinematic / hip-hop / indie lo-fi / surreal ... in your own words]
Not this: [the look to avoid, one line]
## 3. THE WORLD
Setting: [one place, named specifically]
Light: [source + time of day]
Palette: [two or three colours, no more]
Texture: [film grain / clean digital / haze / rain / neon]
## 4. WHAT RECURS
Main figure: [who or what, one line]
Singer: [a photo of the singer, a character you used before, or none]
Appears in: [which song sections]
Recurring object: [the one prop or place that comes back]
## 5. THE ARC, SECTION BY SECTION
Intro: [what we see first]
Verse: [the everyday state]
Chorus: [the biggest image in the video]
Bridge: [what changes]
Outro: [how it resolves]
## 6. HARD RULES
Always: [what must be in every scene]
Never: [what must never appear]
Pacing: [slow and drifting / balanced / fast cuts, in words]
## 7. WHERE IT GOES
Master: [16:9]
Also need: [9:16, a centre crop of the same edit, so keep action centred]
A worked example
Same template, filled in for a mid-tempo synth track. Note how little of it is adjectives.
# MUSIC VIDEO BRIEF — "Long Way Back"
## 1. THE SONG
Track: Long Way Back — second chorus through the bridge
Part: about 60 seconds, not the full song
Feel: mid-tempo synth-pop, 104 BPM, melancholy but moving
Lyric images: headlights, a payphone, the coast road
Faces on screen: no — driver seen from behind or in mirrors only
## 2. THE LOOK
Style: moody cinematic
Not this: glossy, bright, anything that looks like an advert
## 3. THE WORLD
Setting: a coastal motorway at 3am, one closed petrol station
Light: sodium streetlamps and headlights; no daylight anywhere
Palette: sodium orange, deep blue-black, one cold white
Texture: light rain on glass, faint grain
## 4. WHAT RECURS
Main figure: a lone driver, mid-30s, denim jacket
Singer: none, no one sings to camera
Appears in: verse, chorus, outro
Recurring object: the same silver car, always shot low
## 5. THE ARC, SECTION BY SECTION
Intro: empty road, no car yet, rain on tarmac
Verse: interior, hands on the wheel, wipers
Chorus: wide crane over the coast road, car small in frame
Bridge: the petrol station — first time the car stops
Outro: tail lights leaving frame, road empty again
## 6. HARD RULES
Always: it is night, and it is raining
Never: other people, other cars, any interior that isn't the car
Pacing: balanced
## 7. WHERE IT GOES
Master: 16:9
Also need: 9:16 for Reels — keep the car centred
The "never" row is doing more work than any adjective in the document. "No other people, no other cars" is the line that keeps a lonely video lonely across twelve scenes.
What each field actually changes
The brief isn't a mood board. Most rows correspond to something concrete in the studio.
| Brief row | What it changes |
|---|---|
| Part | The director's first question. The ideas, the plan, the storyboard and the video cover only that part, so you never pay to draw scenes you won't use |
| Style, setting / light / palette | The words the three ideas and the plan are written from, and the frame prompt you can read, exactly as sent, for every shot |
| Singer | The reference the frames are drawn from; each idea names who sings it |
| Section-by-section arc | The plan: how the video unfolds scene by scene, mapped to the sections the director heard in your track |
| Hard rules | What the plan has to respect. Check them against the plan, then against the frames |
| Pacing | How the plan cuts the video. Change it in plain words if the first plan is too slow |
| Where it goes | A 16:9 master, with a 9:16 centre crop of the same edit made from the finished screen |
Two rows deserve a note. The style line is the one to keep short. Spend it on nouns rather than adjectives: "Rain-soaked neon alley, single overhead light, one figure, no crowds" beats a paragraph of atmosphere every time.
And the singer row is worth filling in even though holding a face is still not perfect. Describing "a woman in a red coat" in five separate scenes gets you five different women, because each scene is generated from its own text. Uploading her photo as the singer gives you a fixed reference image instead of a description that drifts, which gets you far closer than re-typing, but holding one performer genuinely identical across every scene isn't reliable yet, so treat it as a strong steer rather than a guarantee. The practical hedge is to make the figure recognisable by silhouette, wardrobe and setting as well as by face: a denim jacket and a specific car survive a scene change more dependably than a jawline does. The mechanics are in our guide to reusable AI characters, and the wording itself in how to write an AI character brief that holds.
Where briefs go wrong
Most briefs fail the same handful of ways: adjectives where nouns belong, no prohibition line, and shot-level detail written before the look is agreed.
| Mistake | What you get | Fix |
|---|---|---|
| Adjectives instead of nouns | "Cinematic, emotional, epic" — a generic video | Name the place, the light, the object |
| No "never" line | Crowds, daylight, extra characters drifting in | Write one prohibition; it's the highest-leverage row |
| Describing shots, not the world | You've written a shot list before you've agreed the look | Edit shots on the storyboard, where they belong |
| A character described, not shown | A different face every scene | Upload one reference photo and reuse it, and design the figure to read from wardrobe and silhouette too |
| Length and aspect written in prose | The director still asks which part of the song, and the video is 16:9 | Answer the part question; make the 9:16 file from the finished screen |
| Not deciding who sings | The plan picks for you, and lip-synced shots cost more | Say who sings, or turn lip sync off when you read the plan |
If you want to spend less, plan the performance shots as atmosphere, wides, silhouettes, backs of heads, hands, rather than as a close-up delivering the hook.
To size the brief, our free shot planner turns your song's length and pace into a shot count and a credit estimate.
From brief to storyboard
The brief isn't the plan, it's the input to the plan. Paste the filled-in template into the box where you describe your idea, then answer the director's questions and pick one of the three ideas. The director writes a plan from your brief and your song's sections, and you can change it in plain words ("make the second scene a close up", "no crowd shots"). Note what you don't need: a separate storyboard template. The storyboard is drawn after you approve its price, with a frame for every shot, so the blank grid you'd normally fill in by hand arrives already populated and your job shifts from drawing it to correcting it. Tap any shot to read the frame prompt exactly as sent, and ask for a change in the chat; the director proposes it as a card with its price. The video is not made until you approve it.
Read the plan and then the storyboard against your brief, row by row. Is it night in every scene? Is the car in the chorus? Is anyone in frame who shouldn't be? Fixing it in the plan costs a message. Fixing it after the video is made costs a new version.
If the storyboard step is new to you, how to storyboard a music video covers mapping shots to song sections, and how to make a music video for your song walks the whole flow end to end. A brief is written for the director; a music video treatment is written for everyone else who has to say yes to the idea (how to write one has a template). When you're ready to run it, open the studio with your track and your brief.
You've written the brief. Now run it.
Paste the brief into the box with your song. The director listens, writes the plan, and shows you the storyboard before the video is made.
Open the studioFrequently asked questions
What is a video brief?
A video brief is a short written document that fixes the creative decisions before production starts — the goal, the look, who is on screen, and what must and must not appear. In advertising it's written by a client for an agency. For a music video you're writing it for yourself, or for an AI director, and the job is the same: turn a feeling you have into instructions someone else could follow without asking you a question.
How is a brief for an AI director different from a normal video brief?
Two differences. First, an AI director has no shared context with you, it can't infer that 'like the last one' means the warehouse video, so every recurring element has to be named or given as a photo or a character you used before. Second, part of the brief is answered in the studio as questions rather than written down: which part of the song, who is on screen, whether to lip sync. Standard agency briefs also carry budget, deliverable deadlines and approval chains, which don't apply here, apart from the price you approve before the storyboard and before the video.
How long should a music video brief be?
One page. If it runs longer you're writing a shot list, which is a different document that comes after, the storyboard is where shot-level detail belongs. One constraint keeps it honest: the world section should name one setting, one light source, and no more than three colours. Anything you can't fit is probably a preference rather than a requirement.
Do I need a brief if the AI generates the storyboard for me?
The AI drafts the storyboard either way — the brief decides whether it drafts yours or a plausible generic one. Melodious plans shots against the real structure of your uploaded track, so the timing is right regardless, but the imagery comes from what you described. A vague vision produces a competent video about nothing in particular, and you find out after generating.
What should I leave out of the brief?
Camera-lens jargon, shot-by-shot direction, and anything that duplicates a setting. Naming a lens or a focal length rarely survives into the image; naming a light source and a palette does. Skip shot-level detail because you'll change that on the storyboard by asking in the chat. And don't write the length or aspect ratio as prose, the director asks which part of the song to make, and the video is made in 16:9 with a 9:16 crop of the same edit one tap away.
Can I reuse the same brief for a second video?
Yes, and it's the main reason to write one down. Keep the style, world and recurring-character rows, swap the song and the section-by-section arc, and you get a second video that visibly belongs to the same release. Characters you have used before are listed under Choose from my assets, so you point at the same reference image every time instead of re-typing a description that drifts.