30-second talking video on Sume: Avatar tiers vs Fabric vs H3 Lip Sync
Thirty seconds of talking video costs $5.52 on Avatar Video standard, $7.35 plus, $16.50 max, $5.63 on VEED Fabric 720p and $3.00 on H3 Max Lip Sync at 768p.
Thirty seconds of talking video costs $5.52 on Sume Avatar Video at standard quality, $7.35 at plus, $16.50 at max, $5.625 on VEED Fabric 1.0 at 720p and $3.00 on MiniMax H3 Max Lip Sync at 768p. The jobs take different inputs, so the cheapest is not always the right one.
Prices
Avatar Video bills per output second by quality. Fabric and H3 Max Lip Sync bill per audio second. The 30 seconds here is the same whether you count output or audio.
| Job | Per second | 30 seconds |
|---|---|---|
| Avatar Video, standard | $0.184 | $5.52 |
| Avatar Video, plus (default) | $0.245 | $7.35 |
| Avatar Video, max | $0.55 | $16.50 |
| VEED Fabric 1.0, 720p | $0.1875 | $5.625 |
| VEED Fabric 1.0, 480p | $0.10 | $3.00 |
| MiniMax H3 Max Lip Sync, 768p | $0.10 | $3.00 |
| MiniMax H3 Max Lip Sync, 480p | $0.0625 | $1.875 |
Inputs differ
Avatar Video starts from a ready avatar and a script, or ordered scenes, and Sume accepts 4 to 60 seconds of planned duration. Quality defaults to plus when you omit it, so a call without the field costs $7.35 rather than the standard figure of $5.52. Output resolution is 720p at this time. Creating the avatar is a separate $0.95 charge.
Fabric and H3 Max Lip Sync are audio-driven jobs, so you supply the audio. That makes the cost of the speech a separate line, which for 30 seconds of TTS is a few cents; see the Sume TTS price of $0.0475 per 1,000 characters.
Choosing
If you want the talking head from a script without managing audio, Avatar Video is the single call. Standard is $1.83 cheaper than the default on 30 seconds. If you already have a voice track and a face, H3 Max Lip Sync at 480p is the cheapest line in the table at $1.875. Use Avatar videos docs for fields and the catalog for rates.
This page compares prices and inputs. It does not rank how the faces look; generate one sample from each before you scale.
- Script in, video out: Avatar Video; set
qualityyourself. - Audio and face in hand: Fabric or H3 Max Lip Sync.
- Cheapest at 30 s: H3 Max Lip Sync at 480p.
Reproduce the numbers
Every Sume price on this page comes from the public catalog at https://api.sume.com/v1/catalog, which needs no API key. Fetch it, find the row for the job or model named in the table, and multiply by your own seconds, characters or image count. Sume bills the list price shown in that row, so the catalog figure is the one that applies to your balance.
All figures on this page are Sume's own, as of 2026-10-09. Prices and limits can change, so re-read the catalog and the linked docs before a large run, and keep the arithmetic in a spreadsheet so you can update it in a minute.
Sources
Related posts
More in Comparisons
- 3,000 Nano Banana 2.1 images: Google batch, standard and Sume
At 1K, 3,000 Nano Banana 2.1 images cost $50.40 on Google batch, $100.80 standard and $300 on Sume. At 4K: $170.10, $339 and $600. Sources and arithmetic.
- 37 Nano Banana 2.1 4K images: Google batch vs standard vs Sume
37 four-K Nano Banana 2.1 images cost $2.10 on Google batch, $4.18 on Google standard and $7.40 on Sume. The gap, and when Sume is still the pick.
- 47-second voiceover: Gemini 3.8 Flash TTS vs Sume TTS
A 47-second voiceover rounds to 50 seconds on Gemini 3.8 Flash TTS: $0.01125 now, double from 2027-01-01. Sume TTS charges $0.0475 per 1,000 characters.
- 4K AI video for 10 seconds: Veo 3.1 Fast $3.00, Omni on Sume $3.75
Ten seconds of 4K output: Veo 3.1 Fast lists $0.30 per second and Standard $0.60 on Google; Sume lists Gemini Omni Flash 1.1 at $0.375. Veo Lite has no 4K.
Written by Sume