Face swap for UGC ads: source clip rules (Sume beta)
Sume's beta Avatar Face Swap applies a ready avatar face to a public 4-15 second source video with audio. Required fields, quality tiers and what it rejects.
Sume's Avatar Face Swap beta applies a ready avatar's face onto a public HTTPS source video, planned for about 4-15 seconds with usable audio. Send avatar_handle, video_url and quality to POST /v1/models/sume/avatar-face-swap/v1.0/runs. It is a Beta endpoint, per Face swap.
Requirements
For script-driven talking videos, use avatar videos instead.
| Item | Rule |
|---|---|
quality | Required: standard, plus or max; no default |
video_url | Public fetchable HTTPS URL |
| Rejected URLs | Localhost, private network, non-HTTPS, signed/private, provider task URLs |
| Source length | About 4-15 seconds with usable audio |
| Unsupported fields | Prompts, transcripts, durations, aspect ratio, provider fields |
Polling
Poll GET /v1/jobs/:id/status and /result. Completed resources expose a video_url under media.sume.com; prefer resource_status for readiness.
When it fits
Use it when you already own a short clip with the performance you want and a ready Avatar 1.0 identity.
Sources
Related posts
More in Sume Avatar 1.0
- How to make an AI UGC ad look less staged with Avatar 1.0
Less-staged AI UGC comes from the first frame: phone-style framing, a casual scene prompt, an approved preview, then the final render. The levers Sume exposes.
- Shortest AI avatar video: 4 seconds, from $0.74 on Sume Standard
Sume avatar videos run 4 to 60 seconds. Per-second rates for Standard, Plus and Max, the 4 second floor, and what 15, 30 and 60 second clips cost.
- Introducing Sume Avatar 1.0
Sume Avatar 1.0 is a multi-agent orchestration system as a single avatar model.
- Avatar Face Swap API (Beta): apply an avatar face to a video
Avatar Face Swap 1.0 is a Beta Sume endpoint that applies a ready avatar's face to a short public source video. Required fields, limits, and polling.
Written by Sume