Explainers · music-led, no voiceover · landscape 16:9
How to make a product explainer video
A product explainer does not need a narrator. The strongest version is music-led: every scene boundary is a match cut, so the eye is carried from one idea to the next without a voice telling it what to think. With baz, the Supahub Ad skill produces exactly this — 27 scenes over about 57 seconds, driven by exponential-settle motion, with velocity-matched seams between every scene. You bring the logo, screenshots and integration partners; the skill brings the motion system and the timing spine.
The shortcut: run a skill instead of starting from scratch
A skill is a context file that teaches an AI agent one specific video style — its structure, pacing, typography, motion grammar and sound design. Hand an agent the skill plus your product, and it rebuilds that video for you. The steps below are what the Supahub Ad skill already encodes, so you can follow them by hand or let the skill carry them.
baz is a library of video skills: context files that teach an AI agent a specific motion-graphics style, so it can rebuild that video for your product, with your brand, from your inputs. Run a skill inside your own coding agent — Claude Code, Codex — or directly in the baz editor.
What you need before you start
Required
- Your brand logo and app icon
- The product claims you want to make — the actual sentences, not a brief
Makes it materially better
- Product screenshots of your primary and secondary surfaces
- Integration partner logos, for the integrations beat
- A feature list and your website copy, so the claims come from your own language
- A music bed you have the rights to — the whole cut is timed to it
How to make a product explainer video: step by step
Choose the music first
In a no-voiceover explainer the music is the script. Pick the track before you write a single scene, because its tempo determines how many scenes you get and how long each one lasts. Changing the track later re-times everything.
Write the claims as short, standalone lines
Without a narrator, every idea has to survive as a few words on screen. Write each claim as something readable in under two seconds. If a line needs a subordinate clause, it needs to be two scenes.
Plan the seams, not the scenes
This is the discipline that makes the format work. For each boundary, decide what visually carries across — a shape that becomes another shape, a colour that persists, motion that continues at the same velocity. The seam is the edit; the scene is just what happens between seams.
Keep everything moving
A static frame in a music-led explainer reads as a mistake. Exponential-settle motion — fast in, gently resolving — keeps the frame alive without making it frantic, and gives every element a landing that feels intentional.
Put every cut on a beat
Derive the scene durations from the track's downbeats rather than picking round numbers. Cuts that land on the beat feel inevitable; cuts that land near the beat feel wrong even to viewers who could not say why.
Watch it once with the sound off
If the video still communicates what the product does with no audio, it will work in a muted autoplay feed — which is where most of your views will happen. If it does not, your on-screen copy is doing too little.
What the finished video actually contains
Approximate timings for a ~57 seconds cut. Treat them as a shape to hit, not a spec — the exact durations shift with your script and your music.
| Time | Beat | What is on screen |
|---|---|---|
| 0:00–0:06 | Cold open | A shape or mark in motion establishes the visual language before any claim is made. |
| 0:06–0:20 | The problem, in type | Short kinetic lines, each one scene, match-cut into the next. |
| 0:20–0:42 | Product beats | Screenshots and UI elements enter as objects in the motion system rather than as flat images. |
| 0:42–0:50 | Integrations | Partner logos assemble — the beat that says this fits into your existing stack. |
| 0:50–0:57 | Lockup | Everything collapses into the logo. The last cut lands on the final beat of the track. |
Mistakes that cost you the view
Adding a voiceover later
Do this instead: Commit to no voiceover or write for one from the start. Narration bolted onto a music-cut edit fights the picture — the pacing was designed for the track, not for a voice.
Hard cuts with nothing carrying across
Do this instead: Match-cut every seam. A boundary where nothing persists is where the viewer's attention leaves.
Long sentences on screen
Do this instead: A few words per scene. If it takes longer than two seconds to read, the cut arrives before the viewer has finished.
Choosing music after the edit
Do this instead: Choose it first. The track determines the scene count and durations — retrofitting it means re-timing every seam.
Letting a frame sit still
Do this instead: Keep something in motion at all times. Stillness in this grammar reads as a rendering error, not as a pause.
Run it from your own agent
Skills are designed to run inside a terminal agent like Claude Code or Codex, against a project you control. The same skill produces the same style whether it runs in your agent or in the baz editor.
npm install -g bazaar.it@latest
# Install this skill into your agent (Claude Code, Codex or Cursor)
baz skill add match-cut-product-explainer-reel
baz project create --name "Supahub Ad for my product"
baz prompt "make a product explainer video" --stream-json
baz review --summary --json
baz export start --wait --format mp4 --jsonOperations draw from a prepaid balance. See the CLI reference for the full command set.
Common questions
Why no voiceover?
Most explainer views happen muted in a feed, and a narrator you cannot hear is dead weight. A music-led cut with strong on-screen type communicates with the sound off and rewards you with atmosphere when the sound is on.
What is a match cut, exactly?
A cut where something visually continues across the boundary — a shape morphs into the next shape, a movement carries at the same speed, a colour field persists. It makes 27 separate scenes feel like one continuous idea rather than a slideshow.
Can I use my own music?
Yes, and you should if you have rights to something that fits. The skill times the cut to whatever track you provide. Make sure your licence covers paid distribution if the video will run as an ad.
Do I need video editing experience?
No. The skill carries the editing decisions — shot order, pacing, type treatment, transitions, sound design. You supply the raw material and the facts about your product; the agent assembles the cut. You review it and ask for changes in plain language.
Can I run this in my own coding agent instead of the baz editor?
Yes. Skills are designed to be run from a terminal agent like Claude Code, Codex or Cursor. Install the CLI with `npm install -g bazaar.it@latest`, then `baz skill add <slug>` to pull the skill into your agent. The same skill produces the same style whether it runs in your agent or in the baz editor.
What does it cost?
baz bills against a prepaid dollar balance rather than a seat subscription — you top the balance up and each operation (generation, voiceover, render, export) draws a listed amount from it. There is no per-seat fee to make a video, and the price of each operation is published.
Can I change the video after it renders?
Yes, and this is the point of doing it as code rather than as a flat render. Every scene is a real component you can edit — ask the agent to re-time a beat, swap a screenshot, rewrite a line, or change the accent colour, and only that part rebuilds. You are not re-rendering from scratch each time.
Will every video from this skill look the same?
The grammar is the same — that is what makes it a skill and not a template. The content is not: your brand colours, typography, screenshots, copy and data all come from your inputs. Reusing one skill across a series is a feature, because episode three lands in the same visual language as episode one instead of being rebuilt from scratch.
Related guides
Pick a skill. Get the video.
Run the Supahub Ad skill in your own coding agent, or in the baz editor. Usage comes out of a balance you top up, with a listed price per operation — no seat subscription to make a video.