Dialogue with lip-sync
“A street food chef looks up at the camera mid-service and says “best noodles in the city, trust me” with a grin, woks flaming behind, handheld framing.”
Alibaba · video model
Happy Horse 1.1Generate arena-leading AI video
from 1.4 credits / second · every plan · price breakdown · API playground
Made with Happy Horse 1.1 · Dialogue with lip-sync
Happy Horse 1.1 is Alibaba’s flagship video model — a long-running #1 on the Artificial Analysis Video Arena — generating 3 to 15 second clips at 1080p with native audio and multilingual lip-sync.
Original results
Happy Horse 1.1 examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Image-to-video
“Animate the scene: steam rises, the chef tosses the wok once, ambient market sound builds, the camera holds steady.”
Creative scene
“Horses gallop through shallow water at sunrise, spray catching the light in slow motion, hooves drumming, a low tracking shot alongside.”
Start-frame control
“Use this image as the opening composition.”
Scene brief
“Set the scene as a still before describing its motion and sound.”
Composition brief
“Plan the shot as a still, then hand the motion to the model.”
Where Happy Horse 1.1 fits best
Best uses
- Talking subjects with multilingual lip-sync
- High-fidelity 1080p masters without an upscale pass
- Nine aspect ratios from 21:9 down to 9:21
- Benchmark-grade realism for hero shots
Limits to know
- Made starts at the cheaper 720p tier; 1080p costs more per second.
- Clips top out at 15 seconds; longer continuous takes need Seedance 2.5 or WAN 3.0.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5
- Resolution
- 720p (default in Made), 1080p
- Duration
- 3–15 seconds
- Output formats
- MP4 with audio
- Reference images
- 1
- Processing
- Scales with duration; progress appears in the generation view.
How to use Happy Horse 1.1 in Made
- 1
Write the scene and dialogue
Describe the subject, motion, and camera; put spoken lines in quotes for lip-synced delivery.
- 2
Add a start image if needed
Upload a still to animate at 1080p while keeping its composition.
- 3
Choose format and length
Pick one of nine aspect ratios and a duration between 3 and 15 seconds.
- 4
Review and refine
Check lip-sync, audio, and motion continuity, then refine one instruction at a time.
Compare relevant models
video
FLUX 3
FLUX 3 is Black Forest Labs’ first video model, generating 5 to 20 second clips with natively synchronized audio from a text prompt or a start image, in seven aspect ratios up to 2:1.
Explore model →video
Kling 3 Pro
Kling 3 Pro is the benchmark tier of Kling AI’s third-generation video model, generating 3 to 15 second clips with optional native audio and the cinematic motion the Kling line is known for.
Explore model →video
WAN 3.0
WAN 3.0 is Alibaba’s WAN 3.0 video model at its standard speed and price, generating 2 to 30 second clips at up to 1080p with audio included. WAN 3.0 Prime runs the same inputs faster for about 40% more per second.
Explore model →Continue with a related tool
AI Video Generator
Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
See the tool →AI Image Generator
Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
See the tool →It is Alibaba’s flagship video model, which took the #1 Elo spot on the Artificial Analysis Video Arena in 2026, generating 1080p clips with native audio and multilingual lip-sync.