Talking clip by length: 4, 15, 60 and 300 seconds, Avatar or Fabric

Sume has two routes for a talking clip: Avatar Video for 4 to 60 seconds from a script, and VEED Fabric 1.0 for 1 to 300 seconds from a still plus audio. Pick by length: 4 to 60 seconds, use Avatar Video; between 60 and 300 seconds, use Fabric (or split Avatar Video into several jobs).

Price at four lengths

Avatar Video tier rates are $0.184, $0.245 and $0.55 per second; Fabric is $0.1875 per audio second at 720p and $0.10 at 480p (as of 2026-10-08). A 15-second Plus clip is 15 x $0.245 = $3.675, so the table shows 20 seconds where cents are exact instead.

Where each route stops

Avatar Video rejects scripts that Sume estimates at under 4 or over 60 seconds. Fabric takes duration_seconds from 1 to 300 and audio that must be Sume-hosted and under 10 MB.

Fabric does not write the performance: you bring the audio and a still. Avatar Video generates the performance from your script. For a 4-second clip you need a script of the right length, or a silence beat in a multi-scene plan.

• Under 4 s: Fabric (1 s minimum) if you have audio.
• 4 to 60 s: Avatar Video from a script, or Fabric from audio.
• 60 to 300 s: Fabric from audio, or several Avatar Video jobs joined on Timeline.

Choosing in practice

For a reusable presenter that you want to keep consistent across videos, create the avatar once for $0.95 and stay under 60 seconds per job. For a long voiceover you have already recorded, Fabric is the single-job route and costs $56.25 for the full 300 seconds at 720p.

Practical notes

Quality tiers. quality accepts standard, plus and max. Plus is the default when you omit it. Standard is the fastest Sume execution path, and Max is the highest quality tier with slower turnaround. Because the three differ in both price and speed, decide the tier per stage of your workflow: a quick pass to confirm wording, then a final render once the script is settled.

Output format. Avatar video output is 720p at this time, and the aspect ratio defaults to 9:16 with 1:1, 3:4, 4:3 and 16:9 also accepted. Choose the ratio in the request rather than cropping afterward, since a crop throws away part of a frame you paid for by the second.

Job lifecycle. Every Sume avatar request is job-backed. You submit, store the job id, and poll GET /v1/jobs/{id}/status until it completes, then read GET /v1/jobs/{id}/result. The shared lifecycle also lets you wait with sync or subscribe mode for a limited time instead of polling, and the result carries Sume-hosted artifacts rather than provider URLs, so you never handle a provider queue id. Plan your client around the job, not around a single blocking response.