Salon or barber intro clip: avatar in front of your own shop photo
Put an AI presenter in front of a photo of your salon with the scene photo input. Script, 9:16 default, what a 20-second clip costs, and a consent warning.
For a salon, barbershop or studio, the cleanest setup is a reusable avatar plus a photo of your own space as the scene reference. The talking-video route accepts scene: { "type": "photo", "image_url": "https://..." }, where the URL must be a fetchable public HTTPS image. The result is a presenter placed in a setting that looks like your shop, in 9:16 by default, ready for a booking page or Reels.
The request in plain words
- Create the avatar once (prompt, profile traits, or a reference photo). Creation is billed once at 0.95 dollars per avatar.
- Send
avatar_handle, ascript, and the scene photo URL. Send eitherscriptorvideo_inputs, never both. - Leave
product_imageout unless you are showing a single product, such as a hair-care bottle at the counter. - Poll the job, then read the finished avatar-video resource.
A 20-second script
Short intros work because each sentence carries one booking reason. Try: who the shop is, one thing you do better than a walk-in chain (a specific service, not an adjective), the street or neighbourhood, and how to book. Say the booking link as words only if it is short. Otherwise leave it for the caption of the post, since the clip itself is not the place for a long URL.
Cost
Twenty seconds at the three tiers, no product image, using the fixed avatar-video rates.
| Tier | Rate per second | 20-second clip |
|---|---|---|
| standard | $0.184 | $3.68 |
| plus (default) | $0.245 | $4.90 |
| max | $0.55 | $11.00 |
Do not put your stylist's face on it by accident
If you create the avatar from a reference photo of a real stylist, you need that person's permission for a synthetic version of them speaking words they did not say. A generic presenter built from a prompt or profile traits avoids the question, and the clip should still say it is AI-generated in the post copy. Customers who book expecting the person in the video will notice.
When a photo of the shop is a bad scene
A crowded, dim or reflective photo makes a poor backdrop. Pick a wide shot with open wall behind where the presenter will stand. Use the preview step to check the first frame before paying for the full render, because the preview still shows the composition. If the avatar looks pasted in, change the photo and run a new preview rather than rerendering the video.
Where the clip goes
On a booking page, put the clip above the service list, because it answers the 'is this the right place' question in the first few seconds. On Reels or Shorts, 9:16 is already the default aspect ratio, so no extra setting is needed. For a Google Business-style listing or a website hero, set aspect_ratio to 16:9 or 4:3 explicitly; the route supports 1:1, 3:4, 9:16, 4:3 and 16:9.
Treat quality as a choice per use. A one-off hero video can use max; seasonal promo variants can use standard, which the docs describe as the fastest execution path. If you omit the field, you get plus.
Variants worth rendering
Because the avatar is reusable, one presenter can introduce each service in its own 15-second clip: colour, cuts, treatments. Fifteen seconds at plus is about 3.68 dollars, standard 2.76 and max 8.25. Put each on the matching service page. Keep the scene photo the same across clips so the set looks like one shop, and change only the script. Review the first one with a preview, then render the rest directly.
Sources
Related posts
More in Use cases
- Scam alert video for customers with an AI avatar: script rules
If scammers use your name, a 20-second avatar clip can warn customers. Script rules, the AI label, why it cannot verify anything, and cost by tier.
- How do I make school morning announcements audio with an AI voice?
A 1,500-character daily announcement is 8 cents on Sume TTS, about $14.40 for 180 school days. How to template the script, add Spanish and keep it short.
- How do I make a self-guided walking tour audio with TTS?
A six-stop walking tour at 700 characters a stop is six TTS jobs of 4 cents each, 24 cents on Sume, about 0.9 MB per stop as default mp3.
- Solar roof before and after clip: Wan 3.0 first and last frame, 7 s
Send the bare roof as first_frame and the finished array as last_frame to wan-3.0. A 7-second clip costs $0.88 at 720p on Sume. Rules for matching the photos.
Written by Sume