Avatar video quality settings: standard, plus or max?
Sume's talking avatar video takes quality standard, plus (default) or max. What each means, the other output fields, and how the preview relates to final tier.
Sume's avatar video takes quality: "standard" | "plus" | "max", and plus is the default when you omit it. standard is the fastest execution path, plus is the balanced path, and max is the highest tier with slower turnaround.
The three descriptions are all the Avatar video docs say, read 2026-09-29. They publish no visual comparison and no per-tier price in that page, so test on your own script and read the price from the API.
What do the tiers mean?
| `quality` | Docs description |
|---|---|
standard | Fastest Sume execution path |
plus | Default when omitted; balanced quality path |
max | Highest quality tier; slower turnaround |
What else shapes the output?
aspect_ratio:1:1,3:4,9:16(default),4:3or16:9.resolutionis currently720p.- The duration window is 4 to 60 seconds, from a
scriptor orderedvideo_inputs.
Can I preview before choosing a tier?
Yes. Avatar video previews (POST /v1/avatar-video-previews) produce still frames first. Preview stills are tier-independent, and you can override the final quality when you call /generate-video, so approving a preview does not lock in the tier. See first-frame previews.
How do I choose?
Start with the default plus for a draft. Move to max only for a script you will publish, and use standard when speed matters more, such as a bulk batch of tests. Read the reserve for each tier from the API's price fields before a big run; avatar video pricing per minute explains where to look.
How do I set it in a request?
Add quality next to avatar_handle and one of script or video_inputs.
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: avatar-max-001" \
-d '{
"avatar_handle": "your_avatar_handle",
"aspect_ratio": "9:16",
"quality": "max",
"script": "Here is the one setting that matters."
}'Sources
Related posts
More in Developers
- AI avatar video length limit: 4 to 60 seconds per job
Sume's avatar video accepts an estimated 4 to 60 seconds per job, for scripts, scenes, previews and inline captions. Where it applies and what to do outside it.
- Talking photo AI without watermark: what Sume documents
Sume's docs describe no watermark option for talking photo clips. They do fix the inputs: a still, Sume-hosted audio under 10 MB, 1-300 s or 5-14.8 s by route.
- Team API keys: which wallet does a Sume run charge?
A Sume run charges the workspace its API key belongs to. A team key spends the team wallet; a personal key on a team Format is refused with 403.
- C# text to speech: call a TTS API with HttpClient
Text to speech in C#: POST the text and a voice with HttpClient, poll the job until it finishes, then stream the MP3 from its audio_url to a file.
Written by Sume