Home-exercise reminder clips for a PT clinic: English avatar, cost

Yes, a physical therapy or chiropractic clinic can turn a written exercise reminder into a short English talking-head clip with Sume's Avatar 1.0, and a 30-second clip at the default plus tier costs $7.35. The presenter is a synthetic avatar you create once for $0.95, so the clinic does not need a camera day for every reminder.

This post covers the narrow job of a reminder clip: a friendly presenter, a script that stays on logistics, and captions so the clip works with the sound off. It deliberately leaves out clinical claims. A clip that tells a patient to do a stretch is clinical content, so your clinician writes and signs off on every script. Sume produces the video; it does not review the advice.

What the clip is and is not

Avatar 1.0 is English-only. If your front desk serves speakers of other languages, this endpoint will not speak to them, and voice cloning is an app feature rather than an API one, so the presenter will not sound like your own therapist.

Good scripts for this format are about the clinic, not the body: "Your follow-up is booked for Thursday, bring your exercise sheet", "Our front door moved to the side entrance this week", "Reply to this message to move your appointment". Keep the medical instruction in the handout your clinician already approved, and let the clip point to it.

• Scripts: appointment prep, entrance and parking changes, seasonal hours, how to reschedule.
• Out of scope: diagnosis, dosage-style instructions, promises about outcomes, before and after body claims.
• Review: one named clinician approves each script before the render is queued.

Cost of a reminder series

Avatar 1.0 talking video is billed per second, and the rate depends on the quality tier and on whether you attach a product image. A clinic reminder has no product, so the "no product" column applies. Rates below come from the Avatar video docs and the Sume rate card (read 2026-10-10).

Take five 30-second reminders at the default plus tier: 5 x 30 s x $0.245 = $36.75, plus the one-time $0.95 to create the presenter, for $37.70. The same five at standard come to 5 x 30 x $0.184 = $27.60.

Captions so it works muted

Waiting rooms and phones on silent are the normal viewing condition for a clinic message. Sume can burn the spoken words into the picture. The standalone video captions job costs $0.20 per clip for videos up to 60 seconds and needs a public HTTPS video URL. The talking-video endpoint also accepts an inline captions option, which is a separate add-on, so decide which route you want before you budget.

If you later change the caption look, a restyle of an existing caption job reuses the stored word timings rather than transcribing again, per the same docs page. That is handy when the clinic's brand colors change but the words do not.

A soft background bed

A quiet music bed can make a reminder feel finished. The Music Router charges a fixed $0.125 per track and has no duration field, so you steer the length in the prompt and trim to fit. Keep it instrumental and low, because the avatar voice has to stay intelligible.

Where the clip goes

Short reminders suit text-message links, the patient portal email, and the waiting-room screen. Check each destination's own upload limits before you build the file. For a Google Business Profile post, Google's help page says videos can be up to 30 seconds, up to 75 MB, and 720p or higher (read 2026-10-10, source), so a 30-second reminder fits the duration cap exactly.

Start with one reminder, review the first render with the clinician, then batch the rest. For the same pattern in another appointment business, see the dental marketing post.