Newsletter paid-upgrade pitch as a 45-second avatar clip: cost
What a 45-second talking-avatar pitch for your paid newsletter tier costs on Sume: $8.28 at Standard, $11.03 at Plus. Request body, 4-60 second limit.
A 45-second talking-avatar pitch for a paid newsletter tier costs $8.28 at Sume's Standard quality and $11.03 at Plus, using the per-second avatar rates on the rate card read 2026-10-04: $0.184 and $0.245 per second with no product image. Avatar Video accepts scripts that run 4 to 60 seconds, so a 45-second pitch fits in a single request.
Newsletter platforms keep adding paid tiers and community features, so more writers are asking readers to upgrade. A short face-to-camera pitch in the welcome email is the same ask that works in person, and you only record it once.
What does the pitch say?
Three beats at about 15 seconds each: who the paid issue is for, what they get that free readers do not, and how to upgrade. At a speaking pace of roughly 150 words a minute, 45 seconds is about 110 words. Sume estimates the duration from your script, and anything over 60 seconds is refused, so trim rather than rush.
What are the three quality tiers?
quality accepts standard, plus and max; plus is the default if you omit it, standard is the fastest path and max is the highest quality and slowest (Avatar videos). Aspect ratio defaults to 9:16, and resolution is 720p.
| Quality | Rate per second | 45-second pitch |
|---|---|---|
| Standard | $0.184 | $8.28 |
| Plus (default) | $0.245 | $11.03 |
| Max | $0.55 | $24.75 |
What does the request look like?
You need a ready avatar, either one you created or one from the catalog, referenced by avatar_handle. Send exactly one of script or video_inputs. The request is async: the response is a job, and you read GET /v1/jobs/{id}/status until it is completed.
import os, requests
r = requests.post(
"https://api.sume.com/v1/avatar-1.0/talking-video",
headers={
"Authorization": f"Bearer {os.environ['SUME_API_KEY']}",
"Idempotency-Key": "paid-pitch-001",
},
json={
"avatar_handle": os.environ["AVATAR_HANDLE"],
"aspect_ratio": "9:16",
"quality": "standard",
"script": "If you read me on Tuesdays, Friday is for you. Paid readers get the long issue, the archive and one reply a week. It costs less than a coffee. Tap upgrade below.",
},
timeout=60,
)
print(r.status_code, r.json())Is the pitch worth that price?
Test at Standard and render Plus only for the version you keep. Never resubmit a paid request because your client timed out; read the job instead (Jobs and results). Put the price of your tier in the email text, not in the spoken script, so the clip stays valid when the price changes.
Sources
More in Use cases
- One 16:9 master for Samsung Ads CTV and Quora video ads, under 50 MB
Both take 16:9 MP4 with H.264 and AAC. The shared envelope: 5 to 60 seconds, 1920x1080, 30 fps, under 50 MB. Build it as a Sume timeline and check the size.
- One 9:16 master for Instagram ads: what two Meta pages say
Meta's Instagram Feed video ad page lists 9:16 at 1080x1920 and 4 GB. Its placement chart shows a narrower Feed range. How to pick a master and check it.
- One layout reference, twenty posters: GPT Image 2.5 on Sume
ChatGPT Images 2.5 ships poster templates. On the API, reuse one layout image as a reference and change only the headline: 20 calls.
- One video in three languages: per-language voiceover tracks on Sume
Render scene lines in each language with TTS, join each language into one track with timeline audio concat, then re-base scene starts from segments[].
Written by Sume