Pricing Blog
Alibaba · Video and audio, generated together.

Happy Horse 1.0

A Chart-Topping AI Video Model With Sound Built In

Happy Horse 1.0 is Alibaba's chart-topping generator that produces 1080p video and its synchronized audio in a single pass — dialogue, Foley, and ambient sound included, no dubbing step.

~15B
Parameters (reported)
1080p
Native output
7
Lip-sync languages
#1
Video Arena rank
What's new

A Chart-Topping AI Video Model With Sound Built In

01

Native audio-video

A unified single-stream Transformer emits video frames and their matching soundtrack jointly in one forward pass, so lip movement, dialogue, and ambience are aligned by design rather than stitched afterward.

02

Ranked #1 on the arena

Debuting anonymously, it topped the Artificial Analysis Video Arena in both text-to-video and image-to-video on blind human preference votes, overtaking previous leaders.

03

Multilingual lip-sync

Generates emotionally expressive, lip-synced dialogue across seven languages including English, Mandarin, Cantonese, Japanese, Korean, German, and French.

04

Built-in video editing

Beyond generation, it edits existing footage — restyle a clip or swap in a subject from a reference image while keeping the original motion.

Overview

Model at a glance

Happy Horse 1.0 (stylized HappyHorse-1.0, Chinese 快乐小马) is an AI video generation model from Alibaba that made an unusual entrance: it appeared at the top of the Artificial Analysis Video Arena leaderboard in April 2026 without any company attached to it, and within days Alibaba confirmed it was behind the model. Built within the Alibaba Token Hub (ATH) business unit by a team led by Zhang Di — a former Kuaishou VP and technical architect of Kling AI — it quickly became one of the most talked-about releases of the year, claiming the top ranking in both text-to-video and image-to-video categories on blind human-preference voting.

What sets Happy Horse 1.0 apart technically is native joint audio-video generation. Rather than producing a silent clip and dubbing sound in a separate step, its Transformer (reportedly a roughly 15-billion-parameter single-stream design, not officially confirmed) generates the video and its synchronized soundtrack — dialogue, Foley, and ambient sound — together in one forward pass. Combined with native 1080p output, multi-shot sequences, and lip-synced speech across seven languages, this makes it aimed squarely at end-to-end, ready-to-watch video rather than raw visuals that need a post-production pipeline.

Model
Happy Horse 1.0 (HappyHorse-1.0)
Developer
Alibaba (Alibaba Token Hub, ATH)
Team lead
Zhang Di (ex-Kuaishou / Kling)
Architecture
Reportedly ~15B-parameter Transformer (not officially confirmed)
Inputs
Text, image, reference images, video (editing)
Output
1080p video with native audio
Languages (lip-sync)
7 (EN, ZH, Cantonese, JA, KO, DE, FR)
Leaderboard debut
April 2026, Artificial Analysis Video Arena
Capabilities

Key features

Joint audio-video generation

The model's defining feature is generating picture and sound together in a single pass rather than as two stages. Because audio is produced alongside the frames, lip movement, spoken dialogue, sound effects, and background ambience stay coherent without a separate dubbing or Foley step.

Unified single-stream Transformer

Reports describe a roughly 15-billion-parameter single-stream self-attention Transformer that handles both modalities in one architecture, rather than bolting an audio module onto a separate video generator. This unified design is credited for the tight audiovisual synchronization.

Native 1080p output

Happy Horse 1.0 generates in HD 1080p natively rather than upscaling from a lower base resolution. It also supports multi-shot sequences, allowing a single generation to move between camera angles within one clip.

Multilingual lip-sync

The model produces lip-synced, emotionally expressive dialogue across seven languages — English, Mandarin, Cantonese, Japanese, Korean, German, and French. This makes it well-suited to talking-character and localized content where mouth movement must match the spoken track.

Text, image, reference and video inputs

It accepts text prompts, still images, reference images and existing video as input. Text-to-video builds a scene from a description, image-to-video animates an existing frame or character design, reference-to-video carries a subject from reference images into a new scene, and video editing reworks existing footage.

Benchmark-topping quality

On the Artificial Analysis Video Arena, which ranks models by blind human preference, Happy Horse 1.0 reached the top position in both text-to-video and image-to-video, ahead of previously leading models. It is one of the highest-rated video models on that leaderboard to date.

Proprietary, API-based access

Happy Horse 1.0 is a closed-source, proprietary model: its weights are not publicly available and it is not offered under an open license. You can use it through Alibaba Cloud Model Studio's API, the official HappyHorse website, the Qwen App, and API partners.

Specs

Technical specifications

Model

NameHappy Horse 1.0 (HappyHorse-1.0)
DeveloperAlibaba (Alibaba Token Hub, ATH)
Parameters~15 billion (reported, not officially confirmed)
ArchitectureSingle-stream self-attention Transformer (reported)
AccessProprietary; API via Alibaba Cloud Model Studio

Generation

InputsText prompt, image, reference images, video (editing)
Output resolution1080p HD (native)
AudioNative synchronized audio (dialogue, Foley, ambience)
Multi-shotSupported within a single clip
Lip-sync languagesEnglish, Mandarin, Cantonese, Japanese, Korean, German, French

Recognition

LeaderboardArtificial Analysis Video Arena
Text-to-video rank#1 (blind human preference)
Image-to-video rank#1 (blind human preference)
DebutApril 2026 (anonymous, later attributed to Alibaba)
In practice

Use cases

Talking-character and dialogue clips

Because lip-sync and speech are generated with the video, the model suits avatars, explainers, and character scenes where mouth movement must match spoken lines — across seven languages without a separate voiceover pass.

Ready-to-watch social content

Native audio means short-form clips arrive with ambience and sound effects already attached, cutting the editing loop for creators publishing quickly to social platforms.

Localized video at scale

Multilingual lip-sync makes it practical to produce the same scene in several languages with matching mouth movement, useful for global marketing and education content.

Animating stills and concept art

Image-to-video lets designers and studios bring a single frame, product shot, or character illustration to life with motion and a synchronized soundtrack.

Prototyping and previsualization

Multi-shot 1080p generation with sound helps teams sketch out sequences, mood, and pacing early — a fuller preview than silent draft renders.

Generational leap

Happy Horse 1.0 vs. Seedance 2.0

Happy Horse 1.0 overtook ByteDance's Seedance 2.0 at the top of the Artificial Analysis Video Arena. Here's how the two leading models line up on the headline capabilities.

FeatureSeedance 2.0Happy Horse 1.0NEW
Video Arena rank (T2V, at HH debut)Previous leader#1
Native synchronized audioYes, joint audio-video generationYes, joint audio-video in one pass
Multilingual lip-syncSupported7 languages
License / accessClosed / commercialClosed / API
DeveloperByteDanceAlibaba
Honest look

Current limitations

No open weights

Happy Horse 1.0 is closed source: its weights are not publicly available, so it cannot be downloaded or self-hosted. Claims of an Apache-2.0 release came from websites not affiliated with Alibaba; access is through Alibaba's own channels and API partners.

Benchmark figures vary by snapshot

Reported Elo scores and exact rankings differ between leaderboard captures and categories. Treat specific point values as approximate; the consistent takeaway is a top-tier, #1-class placement rather than one fixed number.

Clip length and per-shot constraints

Like most current video models, generations are short clips rather than long-form video, and complex multi-shot prompts can still produce continuity or artifact issues. Plan for iteration on demanding scenes.

Access differs by platform and version

First-party API access is available on Alibaba Cloud Model Studio, and a newer HappyHorse 1.1 has since been released, so pricing and features can differ between 1.0, 1.1 and partner platforms.

FAQ

Frequently asked questions

Who made Happy Horse 1.0?
It was developed by Alibaba. The model first appeared anonymously atop the Artificial Analysis Video Arena in April 2026, and Alibaba then confirmed it was built within its Alibaba Token Hub (ATH) business unit by a team led by Zhang Di, a former Kuaishou VP and technical architect of Kling AI.
What makes Happy Horse 1.0 different from other video models?
Its standout feature is native joint audio-video generation: a single model (reportedly a ~15B-parameter Transformer, though Alibaba has not confirmed the figure) produces the video and its synchronized soundtrack — dialogue, sound effects, and ambience — in one pass, instead of generating a silent clip and adding audio afterward.
What resolution and audio does it output?
It generates natively in 1080p HD with synchronized audio, including lip-synced dialogue. It supports multi-shot sequences and lip-sync across seven languages: English, Mandarin, Cantonese, Japanese, Korean, German, and French.
Is Happy Horse 1.0 open source?
No. Happy Horse 1.0 is a proprietary model and its weights are not publicly available. You can use it through Alibaba Cloud Model Studio's API, the official HappyHorse website, the Qwen App, and API partners.
How good is it compared to other models?
On the Artificial Analysis Video Arena, which ranks models by blind human preference votes, Happy Horse 1.0 reached #1 in both text-to-video and image-to-video, ahead of previously leading models such as Seedance 2.0. Exact Elo figures vary by leaderboard snapshot.
Does it support both text and image inputs?
Yes. Happy Horse 1.0 supports text-to-video, generating a scene from a written prompt, and image-to-video, animating an existing still image or character design — both with the same native-audio pipeline. It also supports reference-to-video, which builds a clip around subjects from reference images, and editing of existing video.
Can I use Happy Horse 1.0 on SharkFoto?
Yes. Happy Horse 1.0 is available on SharkFoto in Text to Video, Image to Video and Video to Video. Generate 3–15 second clips at 720p or 1080p in 16:9, 9:16, 1:1, 4:3 or 3:4, and add up to 9 reference images.

Create with Happy Horse 1.0 on SharkFoto

Generate 720p or 1080p video with synchronized sound on SharkFoto — set any length from 3 to 15 seconds and start from text, an image, or reference images.

Try Happy Horse 1.0 now