Classroom projector lesson video in 4:3: set the avatar aspect ratio
Avatar Video defaults to 9:16, so a lesson for an older 4:3 projector needs aspect_ratio set to 4:3. Five ratios are supported; resolution is 720p.
For a classroom projector that still shows 4:3, set aspect_ratio to "4:3" on POST /v1/avatar-1.0/talking-video. If you omit it you get the default, 9:16, which is a tall phone-shaped video that will sit as a narrow strip on a projector. Resolution is currently 720p and the duration window is 4 to 60 seconds.
Source: Avatar videos, read 2026-10-04.
Supported ratios
The five supported ratios cover most classroom screens, phones and slide decks.
| aspect_ratio | Typical screen | Notes |
|---|---|---|
| 4:3 | Older projector or interactive whiteboard | Set explicitly |
| 16:9 | Modern projector, laptop, TV | Common for lessons |
| 1:1 | Social post, LMS tile | Square |
| 3:4 | Portrait tablet | Tall |
| 9:16 | Phone vertical | Default if omitted |
Request
Because lesson scripts are often over a minute, split them into several videos. The limit is 60 seconds per video, and inline captions are limited to videos of 60 seconds or less.
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: fractions-lesson-1" \
-d '{
"avatar_handle": "mr_okafor",
"aspect_ratio": "4:3",
"quality": "standard",
"script": "Today we compare fractions with different denominators. Start by finding a common denominator.",
"scene": { "type": "prompt", "prompt": "A classroom whiteboard with a clean marker tray" },
"captions": { "enabled": true, "style": "slam", "language": "en" }
}\Check the frame first
To see the framing before the full render, use Avatar video previews. The aspect ratio is part of the request and cannot be overridden at generate-video, so a wrong ratio means a new preview.
One idea per video
Split a long lesson into several clips of 60 seconds or less, one concept each, and reuse the same avatar_handle and scene so the teacher looks the same across the set. Name each video with title so the set stays in order in your workspace.
Sources
Related posts
More in Use cases
- Clean a transcript with a 2,000-character instruction, then caption
ElevenLabs speech to text can edit a transcript from a natural-language instruction up to 2,000 characters. A cleanup then captions workflow with Sume captions.
- Course welcome video captions in your brand color (slam, $0.20)
Burn captions in your school's accent color: set design.colors.active on the slam style. It does not work on punch or tiktok-green. $0.20 for clips to 60 s.
- Article 50: creator duties vs provider duties, side by side
Article 50(4) puts deepfake and certain text disclosure on deployers, while 50(2) puts marking on providers. A two-column split for teams that publish AI video.
- Case study video narrated by an avatar: three scenes, 55 seconds
Narrate a written case study as a 55-second, three-scene Sume avatar video: problem, change, result. Cost by tier and a body you can send; no names needed.
Written by Sume