H3 Max Lip Sync vs Fabric for an 11.3-second voiceover: $1.20 vs $2.25
An 11.3-second voiceover bills 12 audio seconds: $1.20 on MiniMax H3 Max Lip Sync at 768p and $2.25 on VEED Fabric 1.0 at 720p on Sume.
An 11.3-second voiceover is billed as 12 audio seconds, so MiniMax H3 Max Lip Sync at 768p costs 12 x $0.10 = $1.20 and VEED Fabric 1.0 at 720p costs 12 x $0.1875 = $2.25 on Sume. At 480p the two are $0.75 and $1.20. Both bill by audio length rather than by video resolution alone.
Two per-audio-second products
The catalog prices MiniMax H3 Max Lip Sync at $0.0625 per second at 480p, $0.10 at 768p and $0.20 at 1080p. VEED Fabric 1.0 is $0.10 per second at 480p and $0.1875 at 720p. Both reserve ceil(duration_seconds) x the per-second rate, and both take Sume-hosted audio under 10 MB.
They are different tools. Lip Sync accepts audio of 5-14.8 seconds. Fabric on Sume accepts audio up to 300 seconds, so it is the only one of the two for a 40-second voiceover.
| Audio (s) | Billed seconds | H3 Max Lip Sync 768p ($0.10) | H3 Max Lip Sync 480p ($0.0625) | Fabric 720p ($0.1875) |
|---|---|---|---|---|
| 5 | 5 | $0.50 | $0.3125 | $0.9375 |
| 8.4 | 9 | $0.90 | $0.5625 | $1.6875 |
| 11.3 | 12 | $1.20 | $0.75 | $2.25 |
| 14.8 | 15 | $1.50 | $0.9375 | $2.8125 |
Worked example
For an 11.3-second voiceover: ceil(11.3) = 12. Lip Sync 768p: 12 x $0.10 = $1.20. Lip Sync 1080p: 12 x $0.20 = $2.40. Fabric 480p: 12 x $0.10 = $1.20. Fabric 720p: 12 x $0.1875 = $2.25.
For a set of 50 voiceovers at 11.3 seconds, the totals are $60.00 (Lip Sync 768p) against $112.50 (Fabric 720p), a gap of $52.50.
- Lip Sync audio limit: 5-14.8 s
- Fabric audio limit: 300 s
- Both: Sume-hosted audio, under 10 MB
The 14.8 second edge
Lip Sync rejects audio shorter than 5 seconds and the provider silently clips anything above 14.8 seconds, per the catalog note. A 15-second voiceover is therefore not a safe input; trim it to 14.8 or use Fabric. Splitting audio is a $0.01 job in the catalog.
Check the clip length before submitting; paying for 15 billed seconds of audio that the provider cut at 14.8 would be a waste.
A second scenario
Scale the voiceover count. Thirty voiceovers of 8.4 seconds each bill 9 seconds. Lip Sync at 768p is 9 x $0.10 = $0.90 each, $27.00 in all. Fabric at 720p is 9 x $0.1875 = $1.6875 each, $50.625 in all. The $23.625 difference is the price of choosing Fabric for audio that Lip Sync could handle.
Choosing
Use Lip Sync when your audio is short and you want the lowest price per second. Use Fabric when the voiceover is long or when 720p matters. Test one 12-second sample first: it costs $1.20 or $2.25.
Reproduce the numbers
Open https://api.sume.com/v1/catalog, which needs no key, and find the entry for the product. Each model_pricing row carries price, unit, pricing_basis and the estimated, minimum and maximum cents. Multiply the unit price by your quantity and round only at the end. The catalog also has applied_* fields that include an agent fee of 550 basis points; the figures in this post use the base prices.
Sources
Related posts
More in Pricing
- How many 480p drafts cost one 1080p render? Wan 3.0 and Seedance 2.5
A 9-second Wan 3.0 clip is 4 drafts to 1 final at 1080p; Seedance 2.5 is 5.29 drafts per 1080p. The break-even table, priced from Sume rates.
- How many images does $20 buy on Sume? 100 at 4K to 808 on GPT low
$20 buys 100 Nano Banana 2.1 4K images, 808 GPT Image 2.5 low 1K images, or 800 at the 2.5-cent rows. A table of 14 Sume image prices and whole images per $20.
- Ideogram 4.5 high $0.275 or seven low tries at $0.0375 on Sume?
Ideogram 4.5 on Sume costs $0.0375 low, $0.075 medium, $0.275 high per image. Seven low retries cost $0.2625, less than one high render. Eight cost $0.30.
- Ideogram 4.5 price by quality: fal list vs Sume, per 1,000 images
Ideogram 4.5 is $0.03, $0.06 or $0.22 per image on fal by quality, size-independent. Sume bills list x 1.25: $0.0375, $0.075, $0.275. Per-1,000 table.
Written by Sume