Anam Cara-4 portrait 768x1152 vs Sume 9:16 avatar at 720p
Anam Cara-4 renders natively at 768x1152 portrait. Sume's avatar video defaults to 9:16 at a fixed 720p, with plans estimated at 4-60 seconds.
Sume documents a ratio and a resolution label, not pixel dimensions: aspect_ratio defaults to 9:16 and resolution is currently 720p. Anam states Cara-4 pixel sizes, 1152x768 landscape or 768x1152 portrait. Do not assume the two are the same frame size.
Anam facts are from its Cara-4 post; Sume facts from Generate avatar video, read 2026-10-01.
What does Anam say about Cara-4 resolution?
Cara-4 renders natively in landscape or portrait, 1152x768 or 768x1152, which Anam puts at about 2.5 times the pixels of Cara-3. It adds that portrait is now a first-class output.
What does Sume document?
aspect_ratio supports 1:1, 3:4, 9:16, 4:3 and 16:9, default 9:16. resolution is currently 720p. The pages cited give no width-by-height figures for those, so the comparison table uses the labels the docs use.
| Item | Anam Cara-4 | Sume avatar video |
|---|---|---|
| Portrait | 768x1152 native | 9:16 (default) |
| Landscape | 1152x768 native | 16:9 |
| Resolution term | Pixel sizes | 720p only |
| Length | Live session | 4-60 s estimated script |
Which should I pick for vertical video?
If you need a finished vertical clip from a script, Sume's 9:16 default fits with no extra field. If you need a live conversational avatar, that is Anam's use. Our aspect ratio guide lists all five ratios.
Can I get a higher resolution from Sume?
Not through the avatar route's resolution field, which is 720p today. See avatar video 4K upscale for what the docs say about upscaling.
Sources
Related posts
More in Models
- Dictation API: AssemblyAI cleaned text vs Sume STT word timings
AssemblyAI's Dictation API returns send-ready text. Sume STT returns a transcript with words[] timings and no cleanup flag, so you do the filler removal.
- AssemblyAI text to speech: coming soon, and what Sume has today
AssemblyAI's product menu lists a Text-to-Speech API as coming soon. Sume TTS is available now: what a call takes, the 20000-character cap, and word timings.
- AssemblyAI Universal-3.6 Pro 32 languages vs Sume STT language_code
AssemblyAI streaming defaults to Universal-3.6 Pro with 32 languages; 3.5 Pro has 19. Sume STT 1.0 takes one optional language_code hint and auto-detects.
- Cartesia Sonic 2 and Turbo stop October 20: Sume model ids
Cartesia retires sonic-2 and sonic-turbo on October 20, 2026. Sume's TTS Router lists sonic-3.6, 3.5, 3, latest and preview; here is what to send instead.
Written by Sume