UGC-style spokesperson video script: hook, proof, ask in 45 seconds

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.

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.