Motheia AI
Home Creation Studio ModelsPricingAboutBlogSupport

№ 21 VIDEO MODEL · ALIBABA ATH-AI

HappyHorse 1.0

VIDEO · 6S · 720P–1080P · 7-LANGUAGE LIP-SYNC TEXT → VIDEO IMAGE → VIDEO

HappyHorse 1.0 is Alibaba ATH-AI's unified multimodal video model: 1080p picture and synchronized audio in a single forward pass, with lip-sync across seven languages. Dialogue scenes are its home turf.

What it can do

Model specs from Alibaba ATH-AI; prices are in Motheia credits.

STARTS FROM
Text to video · Image to video (first frame; ratio derives from it)
QUALITY
720p · 1080p
CLIP LENGTH
6 seconds
PRICE
720p · 6s: 1000 credits · 1080p · 6s: 1750 credits
HOW IT IS PRICED
Per generated clip, priced by quality.
NOTES
Lip-sync in English, Mandarin, Cantonese, Japanese, Korean, German, and French; 16:9, 9:16, 1:1, 4:3, 3:4 ratios for text-to-video

The studio shows the exact credit cost before you generate.

Core features

01

Single-pass audio-video

Picture and sound are generated jointly in one Transformer pass.

02

Seven-language lip-sync

Mouth shapes align to the chosen audio language at sub-pixel precision, per published specs.

03

Five aspect ratios

16:9, 9:16, 1:1, 4:3, and 3:4 for text-to-video requests.

04

Fast sampler

Published figures show roughly 38 seconds for a 1080p clip on its reference hardware.

Where it earns its credits

  1. 01

    Talking-head content

    Dialogue-forward clips where lip-sync quality is the point.

  2. 02

    Multilingual campaigns

    One concept voiced across seven supported languages.

  3. 03

    Ambient scenes

    Jointly generated sound and picture for atmospheric shots.

How to use it

Three steps, one balance, no new account per model.

  1. 1.

    Describe the result

    Open the studio, write the scene, motion, and camera direction in plain language.

  2. 2.

    Choose HappyHorse 1.0

    Pick HappyHorse 1.0 in the model selector and choose quality and length; the exact credit cost appears before you commit.

  3. 3.

    Generate and track

    Submit once — the job stays attached to your account, and the result waits in your history even if you leave the page.

HappyHorse 1.0 FAQ

i. What is HappyHorse 1.0?

Alibaba ATH-AI's unified multimodal video model: 1080p video and synchronized native audio generated in a single forward pass, with 3–15 second clips.

ii. How much does HappyHorse 1.0 cost on Motheia?

Pricing starts at 1000 credits for a 720p · 6s clip, with 1080p at 1750. The studio shows the exact cost before you generate.

iii. Which languages does lip-sync support?

English, Mandarin Chinese, Cantonese, Japanese, Korean, German, and French.

iv. Does it support image-to-video?

Yes. Provide a first-frame image; the aspect ratio is then derived from that frame.

v. What parameters does it accept?

Prompt (up to 2500 characters), resolution, duration, aspect ratio for text-to-video, plus optional seed and watermark controls.

MORE HAPPYHORSE

The only HappyHorse entry in the library so far.

FULL MODEL LIBRARY →