vidutils Model

LongCat Avatar 1.5 Multi

Animate two people in one image from separate audio tracks with per-speaker lip sync and turn-taking (up to 64s).

Overview

LongCat Avatar 1.5 Multi is a vidutils model available on the GenVR platform. Animate two people in one image from separate audio tracks with per-speaker lip sync and turn-taking (up to 64s).

Pricing

Billed through GenVR credits

20 credits per 5s at 480p, 40 per 5s at 720p. Meanwhile: max(left,right) audio. Sequential: left+right audio (min 5s, max 64s)

Credits40

Approx. INR₹40.00

Approx. USD$0.4200

Properties

Customizable parameters available for this model.

Required

image_urlstring

Single image with two people (left and right). Clear faces work best.

left_audio_urlstring

Audio track for the person on the left (trimmed to 64s max per job)

right_audio_urlstring

Audio track for the person on the right (trimmed to 64s max per job)

orderenum

left_right / right_left: sequential. meanwhile: both speak at the same time (billed by longer track).

Optional

prompt

string

Guide expression, pose, or visual style for both speakers

resolution

enumDefault: 720p

Output resolution: 480p or 720p

480p720p

seed

integerDefault: -1

Random seed for reproducibility (-1 for random)

Model Info

Categoryvidutils

GenVR Visual App

Experience the power of LongCat Avatar 1.5 Multi through our intuitive visual interface. Experiment with prompts, adjust parameters in real-time, and download your results instantly.

Launch App

Developer API Docs

Integrate this model into your own applications. Access enterprise-grade performance, scalable infrastructure, and detailed documentation for rapid deployment.

Explore API

More in vidutils

Discover other high-performance models in the same category as LongCat Avatar 1.5 Multi.