Job opening video with an AI host: 16:9 and 9:16 versions
A 30-second hiring video with a Sume avatar costs $5.52 on Standard or $7.35 on Plus per aspect ratio. A 16:9 and a 9:16 cut on Plus is $14.70.

A 30-second job-opening video with an avatar host costs $7.35 on the default plus tier. A careers page wants 16:9 and a social post wants 9:16, and aspect_ratio is a single value per request, so you submit two jobs: $14.70 for both on plus, or $11.04 on standard.
Two aspect ratios, two jobs
Avatar Video supports 1:1, 3:4, 9:16, 4:3 and 16:9. Reuse the same script and avatar_handle, change only aspect_ratio, and use a different Idempotency-Key for each. Avatar rates are Sume's charged per-second tier rates from the repo rate card (standard $0.184, plus $0.245, max $0.55 without a product image); confirm them in GET /v1/catalog.
| Quality | One aspect ratio | 16:9 and 9:16 |
|---|---|---|
| standard | $5.52 | $11.04 |
| plus | $7.35 | $14.70 |
| max | $16.50 | $33.00 |
Request
Use scene with a prompt to set the room. Avoid putting salary or legal statements into the spoken script that you have not checked, because the avatar will say whatever the script says.
curl -X POST https://api.sume.com/v1/avatar-1.0/talking-video \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: hiring-backend-169-v1" \
-d '{
"avatar_handle": "recruiter_host",
"script": "We are hiring a backend engineer. You will own our job queue, work with a small team, and ship weekly. Apply on our careers page.",
"scene": { "type": "prompt", "prompt": "Bright modern office, shallow depth of field" },
"aspect_ratio": "16:9"
}'Limits and gotchas
- The scene must stay consistent across a multi-scene video, but two separate aspect-ratio renders are independent jobs.
- Resolution is 720p for every aspect ratio.
- Inline
captionscan be set on the same request; a caption-stage failure is soft, and the clean video still completes.
Sources
Related posts
More in Use cases
- Kids story, five 8-second scenes: Omni $5.00 vs H3 $3.00
Five 8-second scenes cost $5.00 on Gemini Omni Flash 1.1 at 720p, $3.00 on MiniMax H3 at 768p and $4.00 on H3 Max, priced on Sume. Plus a reference body.
- Localize One Ad to Korean: Burned-In Captions With Hangul Styles
Add Korean captions to an ad: why Latin styles return a 400, which Hangul style to pick, how a restyle skips a second transcription, and what a job costs.
- Korean restaurant reel captions in Gmarket Sans: one font field, $0.20
Burn Korean captions on a restaurant reel in Gmarket Sans: set font gmarket-sans, style black-outline, language ko. $0.20 for up to 60 seconds.
- Korean to Japanese voiceover: translate, then TTS with language ja
Sume TTS does not translate: send Japanese text with language ja. A 400-character Japanese line costs $0.01900. Transcribe Korean with STT first.
Written by Sume