How to make a get-ready-with-me video when you have no footage

Last updated 2026-08-16 · 6 min read

What is the short version?

The get-ready-with-me format is a voice, a routine and a series of close shots. If you have not filmed yours yet, the structure can be built first and your own footage dropped in later — which is a better order than filming blind and hoping it cuts together.

1. Go to Vizard Agent and say what the routine covers.
2. Say the voice and energy you want narrating it.
3. Say the feed, the length and whether captions are burned in.

What do you need before you start?

A routine and a register. Vizard Agent writes, voices and assembles, so the decisions that are actually yours are what the video is about and who it sounds like — and if you have your own footage, that changes the result more than anything else on this list.

• What the routine is. The occasion, the products, the order of steps.
• The voice. Youthful and energetic, calm and low, dry and funny. It sets the channel's identity.
• Your own footage, if you have it. Vizard Agent will use yours before sourcing anything.
• The length. Under thirty seconds for a feed.
• Captions. Burned in, always. This format is watched muted.

What do you type into Vizard Agent?

Say what the routine is and how it should sound. Vizard Agent writes the script itself, so a description of the energy and the audience does more work than a written script would — and if you already have one, paste it and it will be used as written.

Prompt

Variants worth knowing:

• Your own clips. Upload them and Vizard Agent cuts your footage to the same structure.
• No voice. Captions and music only is a valid version of this format and cheaper to produce.
• A series. Keep them in one project so the voice and caption style stay identical.

What does Vizard Agent actually do?

Here is the order Vizard Agent worked in on a real get-ready-with-me video. The sequence matters more than the steps: the voice exists before the pictures, and the pictures are cut against the voice rather than the other way round.

1. Checks the workspace for any footage that was provided.
2. Lists the available generation and sourcing tools.
3. Searches the stock library for routine footage, running several searches in parallel.
4. Searches for a youthful, energetic voice and generates the narration.
5. Measures the narration's duration, then transcribes it for precise word timings.
6. Downloads the chosen clips and inspects their dimensions and frame rates.
7. Searches for and downloads a chill background track.
8. Assembles and mixes the clips with the narration and music, then verifies the compiled duration.
9. Generates high-energy vertical captions from the word timings, finds a heavy display font, and burns the captions and header on.

Step 5 is the ordering trick. Vizard Agent transcribed the voice it had just generated so it knew exactly when each phrase lands, which is what lets the footage change on the beat of the sentence instead of every three seconds.

What does the result look like?

From the run this page is written from, probed on the delivered file: 1080x1920, H.264, 30fps, 28.03 seconds, AAC audio. Vertical, under thirty seconds, narrated, scored, with animated captions and a header burned in — a complete post rather than a set of parts.

Vizard Agent extracted frames at key moments and looked at the pacing and caption styling before uploading, then ran a quality check over the finished render.

Under thirty seconds is the working length. The routine has to be established in the first three seconds and finished before the viewer decides they already know how it ends.

Expect tens of minutes rather than minutes. This category was not separately measured; comparable work runs a median of 28 to 38 minutes end to end, and across all projects the median cost by tier is Flash 47, Pro 55, Max 242, Ultra 263 credits.

When does this not work well?

This format is about a person, and a video built entirely from stock footage is about nobody. Vizard Agent can produce something that looks like the format immediately, and looking like it is not the same as being it.

• Stock footage is not you. For a personal channel this is a structure to film against, not a substitute for filming.
• Growth is not an editing problem. A well-cut video helps; posting consistently is what actually moves a small account.
• Product claims are claims. Anything said about skin, results or ingredients is your responsibility.
• Gifted or paid products need disclosure. The rules apply regardless of the size of your following.
• Copying a trending sound is not free. Vizard Agent uses licensable music rather than lifting whatever is trending on the feed this week.
• Every account in this format looks alike. The structure is standard, so the only thing that separates yours is you being in it.

How do you fix a result that came back wrong?

Say what to change and where. Vizard Agent keeps the script, the narration, its measured word timings, every downloaded clip and the caption file as separate pieces, so a rewritten line re-reads only that section, and swapping a clip leaves the voice, the music and the timing exactly where they were.

• "That clip does not match the line." A different clip at the same timing.
• "The voice is too much." A calmer read, everything re-timed to it.
• "Use my own footage instead." Your clips cut against the same script.

How does Vizard Agent compare to doing it yourself?

By hand this is writing a script, recording it, finding footage for every line, and timing the cuts to the read — plus a caption pass. It is a couple of hours for a video that has to be one of many to matter.

Common questions

Can it use my own footage? Yes, and it should. Upload your clips and Vizard Agent cuts them to the same structure instead of sourcing stock footage in their place.

Does it write the script? Yes. Describe the routine and the energy, or paste your own words and Vizard Agent uses them.

Will the captions match the voice? Exactly. They come from word timings measured on the generated narration itself.

How long should it be? Under thirty seconds for a feed. The format loses people quickly once the routine is established.

Can I keep the same voice across videos? Yes. Keep them in one project and Vizard Agent reuses the narrator and the caption style.

Can it add a header at the top? Yes. Vizard Agent sets one in a heavy display font, which is the convention on this format and helps the first frame do its job.

Will this get me views? Vizard Agent makes the video good; what it cannot do is post it regularly for you, which is the part that actually builds an account.