Lip-sync a 12-second micro-drama line: H3 Max $1.21, Fabric $2.26

A speaking close-up in a micro-drama: MiniMax H3 Max lip-sync is $1.21 at 768p, VEED Fabric 1.0 is $2.26 at 720p, with TTS included.

4 min readSume
All posts

Speaking face from a still

Video models do not lip-sync to generated TTS, so the close-up is a still plus a voice.

Prices read 2026-10-07 from the Sume rate card; billed per job, rounded up to the cent
RouteBasis12 s line
MiniMax H3 Max lip-sync, 768p$0.10 per second + TTS $0.01$1.21
MiniMax H3 Max lip-sync, 1080p$0.20 per second + TTS $0.01$2.41
VEED Fabric 1.0, 720p$0.1875 per second + TTS $0.01$2.26

Limits

H3 Max lip-sync audio is 5 to 14.8 seconds; Fabric audio is up to 10 MB.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume