5-minute talking still on Fabric: $56.25 at 720p, $30.00 at 480p

VEED Fabric 1.0 on Sume accepts up to 300 seconds of audio: 300 x $0.1875 is $56.25 at 720p and 300 x $0.10 is $30.00 at 480p.

5 min readSume
All posts

A 300-second (5-minute) talking still on VEED Fabric 1.0 costs $56.25 at 720p and $30.00 at 480p on Sume. 300 seconds is the stated maximum, and the price is per ceil(audio second).

Rates and the 300-second ceiling

The pricing page lists Fabric at $0.1875 per second at 720p and $0.10 per second at 480p, with a maximum of 300 seconds and audio that must be Sume-hosted and under 10 MB. The models page lists the duration_seconds range as 1 to 300.

Fabric cost by audio length, as of 2026-10-08
Audio480p ($0.10/s)720p ($0.1875/s)
60 s$6.00$11.25
120 s$12.00$22.50
180 s$18.00$33.75
240 s$24.00$45.00
300 s$30.00$56.25

Longer than Avatar Video allows

Avatar Video stops at 60 seconds per job. Fabric is the route on Sume for a presenter segment between 1 and 5 minutes when you already have the voice track, because it takes a still and an audio file rather than a script. A 5-minute run is a single job with a single audio URL.

The cost to stretch a 60-second Avatar Plus clip to five minutes the other way is five jobs: 300 x $0.245 = $73.50 at Plus. Fabric at 720p is $56.25 for the same 300 seconds, and at 480p $30.00.

  • Plus Avatar, 300 s in five jobs: $73.50.
  • Fabric 720p, one job: $56.25.
  • Fabric 480p, one job: $30.00.

Check before you submit

Measure the audio, send the integer duration_seconds, and make sure the file is hosted on Sume and under 10 MB. A 10 MB file cannot hold 300 seconds of high-bitrate uncompressed audio, so use compressed audio for the long end of the range.

Practical notes

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.

Media inputs. Any media field, whether product_image, scene.image_url or an avatar image_url, must be a fetchable public HTTPS URL. Sume rejects localhost, private-network and non-HTTPS addresses before it submits anything, so a broken link fails fast instead of consuming a render. Host reference images where Sume can fetch them and keep them available until the job finishes.

Idempotency. The docs examples send an Idempotency-Key header on every create call. Use one key per intended job and reuse it only when you retry the same request. A network timeout followed by a fresh submit with a new key is the one path that can create, and bill, a second job. Keep keys human-readable, such as the campaign and scene, so a support lookup is easy.

Sources

Related posts

More in Pricing

All Pricing posts

Written by Sume