UGC-style spokesperson video script: hook, proof, ask in 45 seconds
A 126-word UGC-style script split into three scenes for Sume Avatar 1.0, with a silence beat, a product image, the request and the per-tier price.
Write a UGC-style spokesperson script as three beats: a 5-second hook, a proof line, and one ask. At 2.8 words a second, 45 seconds is about 126 words, and a 9:16 clip with an optional product image is the default shape in Sume Avatar 1.0.
The hook is the part that decides whether anyone watches the rest. Write it first, say it aloud, and cut it until it fits in about 14 words. Then write the ask, and fill the middle with the single best fact you have.
Beats and budget
Seconds add to 45. The proof scene holds most of the words because it carries the claim.
| Scene | Job | Seconds | Words |
|---|---|---|---|
| hook | A concrete question or claim | 5 | 14 |
| proof | What it did for you, in your own facts | 30 | 84 |
| ask | One action | 10 | 28 |
Cost with a product image
With product_image, the per-second rates rise slightly: $0.194 at standard, $0.258 at plus and $0.58 at max. A 45-second clip is therefore $8.73, $11.61 or $26.10. Without a product image the same clip is $8.28, $11.03 or $24.75.
Use video_inputs when you want scene control, and a silence scene when you want a beat with no speech. A silence scene (voice.type: "silence") needs a duration and must not carry a script.
Preview the first frame at standard to check the avatar, scene and product placement, then render once at plus. A changed script, avatar, scene or aspect ratio needs a new preview, while a quality change alone does not.
Writing rules
The list is a quick review, not a legal check.
- Say a fact you can prove from your own records.
- Avoid health, income or guarantee claims.
- One ask, spoken once.
- Disclose AI generation in the post caption.
- Preview the first frame before the render; changing the script needs a new preview.
Why plus is the default
Sume's default quality is plus. Standard is cheaper for drafts, and max costs more than twice plus. One workable pattern is to approve a script at standard, then render the final at plus.
Captions help UGC-style clips because most are watched muted. Inline captions use the same script text, and styles include slam, punch and tiktok-green.
Sources
Related posts
More in Use cases
- Video ad end card: add a fade-in and fade-out with Timeline
Close an ad with a 1-second fade-out and open it with a 0.5-second fade-in using output.fade_in_seconds and fade_out_seconds in a Timeline 1.0 render.
- Turn a voice memo into a narrated short: transcribe, edit, re-voice
Speak your idea into a phone, transcribe it with Sume STT, tidy the text, then re-voice and caption it. The memo becomes the script, not the audio.
- YouTube watch series button: viewers may land on episode 7 first
A viewer who finds one Short in their feed sees a watch series button, so any episode can be the first they see. Write and render episodes that stand alone.
- What is a consistent story for a YouTube show? AI series checklist
YouTube asks shows for the same characters or hosts, one long story, or one topic. A checklist for keeping an AI-made series consistent across episodes.
Written by Sume